Information processing methods, systems, devices, electronic equipment and storage media

Abstract

This disclosure provides information processing methods, systems, devices, electronic devices, and storage media, relating to fields such as big data processing. A specific implementation scheme includes: obtaining initial entity words from a text object; responding to the existence of matching information for the initial entity words, using the initial entity words as candidate words, and using the matching content as the display content associated with the candidate words, wherein the matching content corresponds to the matching information; updating the text object based on the display content associated with the candidate words, and saving the updated text object as a processed text object. This disclosure enables more efficient and convenient viewing of the content associated with words in a processed text object when displaying it, improving overall efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to the field of big data processing technology. Background Technology

[0002] With the development of computer technology, the amount of data has increased rapidly, allowing users to access and view large amounts of articles in a timely manner according to their needs. However, how to enable users to quickly obtain or view information related to a specific word in an article has become a problem that needs to be solved. Summary of the Invention

[0003] This disclosure provides an information processing method, system, apparatus, electronic device, and storage medium.

[0004] According to a first aspect of this disclosure, an information processing method is provided, comprising:

[0005] Retrieves the initial entity words from the text object;

[0006] In response to the existence of matching information for the initial entity word, the initial entity word is used as a candidate word, and the matching content is used as the display content associated with the candidate word, wherein the matching content corresponds to the matching information;

[0007] The text object is updated based on the display content associated with the candidate words, and the updated text object is saved as a processed text object.

[0008] According to a second aspect of this disclosure, an information processing system is provided, comprising:

[0009] A first server is configured to obtain initial entity words from a text object; in response to the existence of matching information for the initial entity words, the server uses the initial entity words as candidate words and the matching content as the display content associated with the candidate words, wherein the matching content corresponds to the matching information; the server updates the text object based on the display content associated with the candidate words, and saves the updated text object as a processed text object.

[0010] According to a third aspect of this disclosure, an information processing apparatus is provided, comprising:

[0011] The initial processing module is used to obtain the initial entity words in the text object;

[0012] The content processing module is used to respond to the existence of matching information for the initial entity word, to use the initial entity word as a candidate word, and to use the matching content as the display content associated with the candidate word, wherein the matching content corresponds to the matching information;

[0013] The update module is used to update the text object based on the display content associated with the candidate words;

[0014] The storage module is used to save the updated text object as a processed text object.

[0015] According to a fourth aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] The memory is communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0019] According to a fifth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the aforementioned method.

[0020] According to a sixth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the aforementioned method.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description.

[0022] The solution provided in this embodiment can obtain the initial entity words in the text object, and then, if there is matching information for the initial entity, use the initial entity words as candidate words, determine the display content of the candidate words, update the text object based on the display content associated with the candidate words, and save it as a processed text object; thus, when displaying the processed text object, it is possible to view the content associated with the words in the processed text object more efficiently and conveniently, thereby improving overall efficiency. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1 This is a flowchart illustrating an information processing method according to an embodiment of the present disclosure. Figure 1 ;

[0025] Figure 2 This is a schematic diagram of the training process of a target model according to an embodiment of the present disclosure;

[0026] Figure 3This is a flowchart illustrating an information processing method according to an embodiment of the present disclosure. Figure 2 ;

[0027] Figure 4 This is a schematic diagram of the composition structure of an information processing system according to an embodiment of the present disclosure. Figure 1 ;

[0028] Figure 5 This is a schematic diagram of the composition structure of an information processing system according to an embodiment of the present disclosure. Figure 2 ;

[0029] Figure 6 This is a schematic diagram of the composition structure of an information processing apparatus according to another embodiment of the present disclosure;

[0030] Figure 7 This is a schematic diagram of another component structure of an information processing apparatus according to another embodiment of the present disclosure;

[0031] Figure 8 This is a block diagram of an electronic device used to implement the retrieval method of the embodiments of this disclosure. Detailed Implementation

[0032] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0033] The first aspect of this disclosure provides an information processing method, such as... Figure 1 As shown, it includes:

[0034] S101: Retrieve the initial entity words in the text object;

[0035] S102: In response to the existence of matching information for the initial entity word, the initial entity word is used as a candidate word, and the matching content is used as the display content associated with the candidate word, wherein the matching content corresponds to the matching information;

[0036] S103: Update the text object based on the display content associated with the candidate words, and save the updated text object as a processed text object.

[0037] The information processing method provided in this embodiment can be applied to the first server.

[0038] The text object can be any one of the multiple candidate text objects stored on the first server side. It should be understood that each of the multiple candidate text objects stored on the first server side can be used as the text object for processing using the information processing method provided in this embodiment; therefore, detailed descriptions are not provided. Specifically, the text object can be an article to be processed; the candidate text object can specifically refer to a candidate article.

[0039] The process of obtaining initial entity words in a text object may include: matching the text object with a preset lexicon and using the entity words in the text object that match preset words in the preset lexicon as the initial entity words; or, processing the text object based on a target model to obtain the initial entity words contained in the text object.

[0040] The preset vocabulary can be pre-set according to actual conditions; the types of words included in the preset vocabulary can also be set according to actual needs, such as medical words or pharmaceutical words, etc.

[0041] The target model can be a pre-trained model, the input of which can be the text object, and the output of which can include the initial entity words contained in the text object.

[0042] After obtaining the initial entity word in the text object, in response to the existence of matching information for the initial entity word, the initial entity word can be used as a candidate word, and the matching content can be used as the display content associated with the candidate word, wherein the matching content corresponds to the matching information.

[0043] Specifically, it can be done by: determining whether the initial entity word has matching information in a preset information database; if the initial entity word has matching information in the preset information database, using the initial entity word as a candidate word and the matching content as the display content associated with the candidate word, wherein the matching content corresponds to the matching information.

[0044] In addition, the method may further include: determining that the initial entity word is not a candidate word when there is no matching information for the initial entity word in the preset information database.

[0045] The preset information database can be pre-stored by the first server. The preset information database may include preset key information and its associated preset content; the number of preset key information pieces can be one or more, and the preset content associated with each preset key information piece can be one or more, without limitation on their quantity. Specifically, the preset information database can be a key-value (KV) database; correspondingly, the preset key information and its associated preset content can be KV pairs.

[0046] In the solution provided in this embodiment, the preset information database can specifically be a preset information database in the medical (or pharmaceutical) field. The preset key information in the preset information database can include: medical entity knowledge concepts, such as at least one of synonyms, hypernyms, and hyponyms for symptoms, diseases, and drugs. The preset content corresponding to the preset key information in the preset information database can represent a department corresponding to a certain disease (or symptom), or an online store corresponding to a certain drug, etc. That is, the concepts contained in the preset key information can be normalized and mapped to standard online drug databases, standard disease databases, etc., which is not exhaustive in this embodiment.

[0047] The matching information is one of the preset key information in the preset information database; correspondingly, the matching content corresponds to the matching information, that is, the matching content is the preset content associated with the matching information.

[0048] It should be understood that the number of candidate words contained in the text object can be one or more, and this embodiment does not limit the number.

[0049] The displayed content corresponding to the candidate words can be the matching content.

[0050] By adopting the above scheme, the initial entity words in the text object are obtained. Then, if there is matching information for the initial entity, the initial entity words are used as candidate words, and the display content of the candidate words is determined. The text object is updated based on the display content associated with the candidate words and saved as a processed text object. Thus, when displaying the processed text object, the content associated with the words in the processed text object can be viewed more efficiently and conveniently, improving the overall efficiency.

[0051] In one implementation, obtaining the initial entity words in the text object may include:

[0052] Retrieve the sentences contained in the text object;

[0053] The sentence segment is input into the target model to obtain the sentence segmentation recognition result output by the target model;

[0054] If the entity word type contained in the sentence segmentation recognition result is a preset type, the entity word is used as the initial entity word, and the position of the initial entity word in the text object is determined based on the sentence segmentation position information of the entity word contained in the sentence segmentation recognition result.

[0055] The step of obtaining the sentences contained in the text object may include: segmenting the text object to obtain at least one paragraph contained in the text object; and processing the at least one paragraph to obtain multiple sentences contained in the at least one paragraph.

[0056] The step of inputting the sentence into the target model to obtain the sentence recognition result output by the target model can specifically include: inputting the multiple sentences into the target model respectively to obtain the sentence recognition result corresponding to the multiple sentences output by the target model respectively.

[0057] The sentence recognition results corresponding to each of the multiple sentences may include: the type of entity word, the sentence position information of the entity word, and the entity word itself.

[0058] After inputting the sentence segmentation into the target model and obtaining the sentence segmentation recognition result output by the target model, it can include:

[0059] Determine whether the type of entity word contained in the recognition result of the i-th sentence corresponding to the i-th sentence among the multiple sentences is a preset type; i is an integer greater than or equal to 1;

[0060] If the entity word in the i-th sentence recognition result is of a preset type, the entity word is used as the initial entity word.

[0061] Additionally, it may include: if the type of the entity word contained in the i-th sentence recognition result is not a preset type, then the entity word shall not be used as the initial entity word.

[0062] The preset type can be set according to the actual situation, such as medical, medical, etc., which will not be listed here.

[0063] Determining the position of the initial entity word in the text object based on the sentence segmentation position information of the entity word contained in the sentence segmentation recognition result may include:

[0064] Based on the sentence position information of the entity word contained in the i-th sentence recognition result, and the j-th paragraph in which the i-th sentence is located, the relative position of the initial entity word in the j-th paragraph is determined; j is an integer greater than or equal to 1.

[0065] The position of the initial entity word in the text object is determined based on the relative position of the j-th paragraph in the text object and the relative position of the initial entity word in the j-th paragraph.

[0066] The step of determining the relative position of the initial entity word in the j-th paragraph based on the sentence position information of the entity word contained in the i-th sentence recognition result and the j-th paragraph in which the i-th sentence is located may include: determining the starting position and length of the initial entity word in the j-th paragraph based on the starting position of the i-th sentence in the j-th paragraph, the starting position and length of the entity word contained in the i-th sentence recognition result in the i-th sentence.

[0067] The clause position information of the entity word refers to the position of the entity word in the i-th clause; the clause position information of the entity word may specifically include: the starting position and length of the entity word in the i-th clause.

[0068] For example, if the i-th clause is clause A1, the clause position information for a certain entity word includes: the starting position of the entity word in clause A1 is the B1th character, and its length is C1. The starting position and length of the i-th clause in paragraph j are: the starting position of clause A1 in paragraph j is the B2th character, and its length is C2. Therefore, the starting position and length of the initial entity word in paragraph j can be determined to be: the B2+B1th character in paragraph j, with a length of C1.

[0069] The step of determining the position of the initial entity word in the text object based on the relative position of the j-th paragraph and the relative position of the initial entity word in the j-th paragraph can specifically include:

[0070] Based on the starting position of the j-th paragraph in the text object, the starting position and length of the initial entity word in the j-th paragraph, the starting position and length of the initial entity word in the text object are determined.

[0071] For example, the starting position and length of the initial entity word in the j-th paragraph can be: the B2+B1th character in the j-th paragraph, with a length of C1. The starting position of the j-th paragraph in the text object is the B3th character. Therefore, the starting position and length of the initial entity word in the text object can be: the B3+B2+B1th character, with a length of C1.

[0072] Thus, by adopting the above scheme, sentences in a text object can be identified based on the target model, yielding sentence identification results. If the entity words in the sentence identification results are of a preset type, these entity words are used as initial entity words. This model-based sentence segmentation avoids the problems of information loss and erroneous parsing that arise when parsing long texts, ensuring both accuracy and efficiency. Furthermore, after determining the initial entity words based on the sentence identification results, restoring these initial entity words to their absolute positions within the text object ensures that the word position information provided for online display is reliable.

[0073] In one implementation, the step of displaying the matched content as associated with the candidate words includes:

[0074] If, based on at least one of the matched content and the candidate words, a preset condition is met, the matched content is used as the display content associated with the candidate words in the text object, and the candidate words in the text object are set to a first display state.

[0075] Specifically, this may include:

[0076] Based on the matched content and at least one of the candidate words, determine whether a preset condition is met; if the preset condition is met, use the matched content as the display content associated with the candidate word in the text object, and set the candidate word in the text object to a first display state; if the preset condition is not met, do not use the matched content as the display content associated with the candidate word in the text object, and set the candidate word in the text object to a first display state.

[0077] Setting the candidate words in the text object to not be in the first display state can specifically mean setting the candidate words in the text object to remain in the second display state.

[0078] The first display state can refer to displaying the text using a preset color. The second display state can refer to displaying the text using a normal color. The second display state can also represent the display state (or color) of other articles in the text object besides those identified as candidate words. The preset color is different from the normal color. The preset color can be set according to actual conditions, for example, it can be red, or other colors; the normal color can be black, or other colors; as long as the preset color is different from the normal color, it is within the protection scope of this embodiment.

[0079] Thus, by adopting the above scheme, the matching content can be used as the display content associated with the candidate word in the text object only when at least one of the matching content and candidate words meets the preset conditions. This avoids the problem of not being able to quickly find the required candidate word due to a large number of candidate words associated with the display content in the text object, thereby improving subsequent efficiency.

[0080] In one implementation, the specific process of determining whether a preset condition is met based on the matched content and at least one of the candidate words may include at least one of the following:

[0081] If the candidate word is located at a preset position in the text object, the preset condition is determined to be met.

[0082] If there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, then the preset condition is determined to be satisfied.

[0083] If the matched content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than a preset threshold, then the preset condition is satisfied.

[0084] The preset location may include locations other than the following: the first-level heading of the text object (i.e., the article to be processed), the summary of the text object (i.e., the article to be processed), and the accompanying image of the text object (i.e., the article to be processed). In other words, if the candidate word is located in any one of the first-level heading, the summary, or the accompanying image of the text object (i.e., the article to be processed), then the preset condition is determined not to be met; otherwise, the preset condition is determined to be met.

[0085] The position of the candidate word in the text object preceding other candidate words can mean that, compared to the positions of other candidate words that are the same as the candidate word, the candidate word is the first one to appear in the text object. In other words, compared to other candidate words that are the same as the candidate word, the candidate word is appearing for the first time in the text object.

[0086] This means there is a limit to the number of times a candidate word or other identical candidate words can appear within a text object. The reason for this setting is that if the same candidate word (or candidate entity word) appears multiple times in a text object, it can lead to an excessive number of identical candidate words and their associated display content within the same text object. By setting the above preset condition, subsequent settings can be applied only to the first appearance of a candidate word or the first word appearing in the text object, thus avoiding the aforementioned problem.

[0087] Other candidate words that are the same as the candidate word may include: other candidate words that are the same as the candidate word, and / or other candidate words that have the same meaning as the candidate word.

[0088] Other candidate words that have the same meaning as the candidate word can be at least one of the following: aliases of the candidate word, synonyms of the candidate word, hypernyms of the candidate word, and hyponyms of the candidate word.

[0089] For example, the text object (i.e., the article to be processed) contains candidate word-1 and other candidate words-2 with the same text. Candidate word-1 appears before the other candidate words-2 in the text object (i.e., the article to be processed), meaning it is the first occurrence of candidate word-1 in the text object (i.e., the article to be processed). Therefore, candidate word-1 satisfies the preset condition. Correspondingly, the other candidate words-2 do not satisfy the preset condition. In other words, when a candidate word first appears, it is set to a first display state (e.g., set to red), thereby avoiding too many candidate words in the first display state on the entire text object page.

[0090] For example, the text object (i.e., the article to be processed) contains candidate word-1 and other candidate words-3 with the same meaning. These other candidate words-3 can be aliases of candidate word-1. Candidate word-1 appears before other candidate words-3 in the text object (i.e., the article to be processed), meaning it is the first occurrence of candidate word-1 in the text object (i.e., the article to be processed). Therefore, candidate word-1 satisfies the preset condition. Correspondingly, other candidate words-3 do not satisfy the preset condition. In other words, if a candidate word (or entity word) is mentioned multiple times in the article using different names (i.e., other candidate words with the same meaning exist), only the first occurrence of the candidate word is set to the first display state (e.g., set to red), thus avoiding an excessive number of candidate words in the first display state across the entire text object page.

[0091] The candidate object can specifically refer to a certain drug or other types of objects, etc., which will not be exhaustively listed here. That is to say, restrictions can also be imposed on the inventory (i.e., remaining quantity) of the candidate object. Taking a drug as an example, it is possible to query whether the drug has sufficient inventory (i.e., remaining quantity). Only when its inventory (i.e., remaining quantity) is greater than a preset quantity threshold is it determined that the preset condition is met. Then, the display content associated with the candidate word can be determined, and the candidate word can be set to the first display state (i.e., set to red).

[0092] The preset quantity threshold can be set according to the actual situation, such as 100, 10, more or less, without limitation.

[0093] It should be understood that the above three judgments on whether the preset conditions are met can be used individually, any two can be used in combination, or all three can be used.

[0094] For example, the specific process of determining whether a preset condition is met based on the matched content and at least one of the candidate words may include:

[0095] If the position of the candidate word in the text object is a preset position, determine whether there are other candidate words in the text object that are the same as the candidate word; if there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, determine that the preset condition is met.

[0096] For example, the specific process of determining whether a preset condition is met based on the matched content and at least one of the candidate words may include:

[0097] If the candidate word is located at a preset position in the text object, determine whether the matched content contains a candidate link and whether the remaining number of candidate objects associated with the candidate link is greater than a preset number threshold; if the matched content contains a candidate link and the remaining number of candidate objects associated with the candidate link is greater than the preset number threshold, determine that the preset condition is met.

[0098] For example, the specific process of determining whether a preset condition is met based on the matched content and at least one of the candidate words may include:

[0099] If there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, determine whether the matching content contains candidate links and whether the remaining number of candidate objects associated with the candidate links is greater than a preset number threshold; if the matching content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than the preset number threshold, determine that the preset condition is met.

[0100] For example, the specific process of determining whether a preset condition is met based on the matched content and at least one of the candidate words may include:

[0101] If the candidate word is located at a preset position in the text object, determine whether there are other candidate words in the text object that are the same as the candidate word. If there are other candidate words in the text object that are the same as the candidate word, and the candidate word is located before the other candidate words in the text object, determine whether the matching content contains candidate links and whether the remaining number of candidate objects associated with the candidate links is greater than a preset number threshold. If the matching content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than the preset number threshold, determine that the preset condition is met.

[0102] It should be noted that the above process of using any two in combination to determine whether the preset conditions are met is only an example. In actual processing, the order of judgment when any two are used in combination may be the same as or different from the above example. Similarly, the process of using all three to determine whether the preset conditions are met is only an example. In actual processing, the order of judgment when all three are used may be the same as or different from the above example.

[0103] As can be seen, by adopting the above scheme, it is possible to determine whether the preset conditions are met by combining at least one of the candidate words and the matched content. This makes the setting of candidate words in the text object more reasonable and clearer, and ensures the efficiency of subsequent client use.

[0104] In one implementation, such as Figure 2 As shown, the method further includes:

[0105] S201: Train the first preset model based on the first training sample to obtain the first model; the first training sample is the training sample in the first sample set;

[0106] S202: The second preset model is trained based on the second training samples and the first model to obtain the trained second preset model, and the trained second preset model is used as the target model; the second training samples are the training samples in the second sample set; the number of training samples in the second sample set is greater than the number of training samples in the first sample set.

[0107] The first training sample and the second training sample come from different sample sets.

[0108] The first training sample is the training sample in the first sample set. The number of the first training samples is not limited in this embodiment. Multiple first training samples can be used to train the first preset model.

[0109] Any training sample contained in the first sample set and the second sample set can be a sentence data with labeled entity words, such as the starting position and length of medical entity words in the sentence data.

[0110] The first sample set and the second sample set contain different numbers of training samples; the first sample set contains fewer training samples than the second sample set.

[0111] The first preset model differs from the second preset model in structure or architecture; the second preset model can be a lightweight model. For example, the first preset model can employ a structure combining an Enhanced Representation from kNowledge IntEgration (ERNIE) model and a Conditional Random Field (CRF). This structure possesses strong feature extraction and generalization capabilities, achieving high analytical performance even with a limited number of samples. The second preset model can employ a structure combining a Gated Recurrent Unit (GRU) neural network and a CRF.

[0112] After obtaining the first model through training, the first model can be used as the teacher model. Then, the second preset model is trained based on the second training samples and the first model to obtain the trained second preset model.

[0113] The training of the second preset model based on the second training samples and the first model may specifically include:

[0114] The second training sample is input into the first model and the second preset model respectively to obtain the first result output by the first model and the second result output by the second preset model.

[0115] The first result is used as a soft label, and a first loss function is obtained based on the soft label and the second result; a second loss function is obtained based on the annotation information of the second training sample and the second result.

[0116] The second preset model is updated based on backpropagation using the first loss function and the second loss function.

[0117] By adopting the above approach, a lightweight target model can be trained using the analytical capabilities of the teacher model. This ensures that the target model is easy to deploy and has a fast prediction speed while maintaining its accuracy.

[0118] In one embodiment, the method further includes:

[0119] If the preset period is reached, all currently saved text objects are processed individually, that is, the aforementioned processes S101-S103 are executed for each currently saved text object. All text objects can be all candidate text objects saved by the first server.

[0120] The preset period can be set according to the actual situation. For example, if the number of all currently saved text objects reaches a first threshold, the preset period is determined to be the first period; if the number of all currently saved text objects does not reach the first threshold, the preset period is determined to be the second period, and the second period is shorter than the first period.

[0121] Furthermore, when the number of all currently saved text objects reaches a first threshold, the preset period is determined as the first period. In addition to processing all currently saved text objects individually when the first period is reached, the method may further include: processing newly added text objects in real time when the first period has not been reached. That is, when the number of all currently saved text objects reaches the first threshold, in addition to periodically processing all currently saved text objects individually based on the first period, the aforementioned processing steps S101-S103 can also be performed on newly added text objects.

[0122] The first threshold can be set according to the actual situation, such as a value in the hundreds of millions; the first period can also be set according to the actual situation, such as one week (7 days), or 15 days, or longer or shorter.

[0123] For example, for hundreds of millions of text objects, a distributed processing approach with a first cycle of 7 days (i.e., weekly) can be used to process all the text objects separately; at the same time, for daily incremental data (i.e., text objects added in real time), streaming real-time processing can be used.

[0124] If the number of currently saved text objects does not reach the first threshold, the preset period is determined as the second period. If the second period is reached, all currently saved text objects are processed individually. The second period can be set according to actual conditions, such as 1 hour, 2 hours, or more or less; it is not limited here. In other words, in small-scale and frequently updated scenarios, a second period (i.e., hourly) can be used to process all currently saved text objects individually.

[0125] After the aforementioned processing is completed, the processed text objects can be stored on the first server side, and the first server side can store the processed text objects in an offline article database. The number of processed text objects can be one or more, and this embodiment does not limit it.

[0126] In one embodiment, the method may further include: in response to receiving a target text object acquisition request from a target device, selecting a target text object from the processed text objects and sending the target text object to the target device.

[0127] The target text object is one of the processed text objects.

[0128] The target device can be a terminal device used by the user, such as any one of a smartphone, tablet, laptop, or personal computer.

[0129] The target text object acquisition request may include relevant information about the target text object, which may include at least one of the following: the identifier of the target text object, the number of the target text object, and the name of the target text object.

[0130] The step of responding to receiving a target text object acquisition request from a target device, selecting a target text object from the processed text objects, and sending the target text object to the target device may specifically include: responding to receiving a target text object acquisition request from a target device, acquiring relevant information about the target text object based on the target text object acquisition request; selecting the target text object from the processed text objects based on the relevant information about the target text object; and sending the target text object to the target device.

[0131] As can be seen, by adopting the above scheme, one of the processed text objects of the identified candidate words and their associated display content can be sent to the target device as the target text object. This allows users to more conveniently view the display content associated with the target words when viewing the target text object on the target device.

[0132] In one implementation, sending the target text object to the target device includes:

[0133] The candidate words contained in the target text object are validated to obtain a validation result; the target text object is adjusted based on the validation result to obtain an adjusted target text object, and the adjusted target text object is sent to the target device.

[0134] The step of verifying the candidate words contained in the target text object to obtain a verification result may include: obtaining the current candidate word based on the position of the k-th candidate word in the target text object; determining whether the current candidate word is consistent with the k-th candidate word; if they are consistent, the verification result is a pass; otherwise, the verification result is a fail. Here, k is an integer greater than or equal to 1. The k-th candidate word is any one of all candidate words contained in the target text object; that is, each candidate word is verified using the aforementioned method, but this will not be elaborated upon further.

[0135] The step of adjusting the target text object based on the verification result to obtain the adjusted target text object includes: if the verification result is that the current candidate word is consistent with the k-th candidate word, no processing is performed; if the verification result is that the current candidate word is inconsistent with the k-th candidate word, the display content associated with the k-th candidate word is deleted, and the display state of the k-th candidate word is adjusted from the first display state to the second display state.

[0136] The second display state can be different from the first display state. The first display state can refer to displaying the text using a preset color. The second display state can refer to displaying the text using a normal color. The second display state can also represent the display state (or color) of other text items in the text object besides those identified as candidate words. The preset color is different from the normal color. The preset color can be set according to actual conditions, for example, it can be red, or other colors; the normal color can be black, or other colors; as long as the preset color is different from the normal color, it is within the protection scope of this embodiment.

[0137] It should be noted that the position of the kth candidate word in the target text object can be obtained from the sentence recognition result output by the aforementioned target model when the target text object is processed as described above. The specific acquisition method will not be repeated here.

[0138] By adopting the above scheme, the candidate words contained in the target text object can be verified again before sending the target text object to the target device, so that the candidate words in the target text object displayed on the target device side are more accurate, thus ensuring the accuracy of subsequent queries and displays.

[0139] In one embodiment, the method may further include: in response to receiving a target word content acquisition request from the target device, acquiring display content associated with the target word, and sending the display content associated with the target word to the target device; wherein the target word is one of the candidate words contained in the target text object.

[0140] In other words, the display content associated with the candidate words contained in the target text object can be stored on the first server side. When a target word content retrieval request is received from the target device, the display content associated with the target word can be found based on the target word content retrieval request, and the display content can be sent to the target device.

[0141] Alternatively, when selecting a target text object from the processed text objects and sending it to the target device, all candidate words contained in the target text object and their associated display content are also sent to the target device. In this approach, the target device can directly respond to the target word content retrieval request and display the content associated with the target word at a preset location. That is, this method eliminates the need for the target device to interact with the first server to complete the display process.

[0142] As can be seen, by adopting the above solution, the target device can be provided with display content associated with any one of the target words when displaying the target text object, ensuring that the target device can display the display content associated with the target words in a timely and accurate manner.

[0143] Finally combined Figure 3 The information processing method provided in the first aspect embodiment above will be described by way of example:

[0144] S301: Retrieves the sentences contained in the text object; the text object can specifically be the article to be processed.

[0145] S302: Input the sentence segmentation into the target model to obtain the sentence segmentation recognition result output by the target model;

[0146] S303: If the type of entity word contained in the sentence segmentation recognition result is a preset type, the entity word is used as the initial entity word, and the position of the initial entity word in the text object is determined based on the sentence segmentation position information of the entity word contained in the sentence segmentation recognition result;

[0147] S304: In response to the existence of matching information for the initial entity word, the initial entity word is used as a candidate word;

[0148] S305: If, based on at least one of the matched content and the candidate words, a preset condition is met, the matched content is used as the display content associated with the candidate words in the text object, and the candidate words in the text object are set to a first display state.

[0149] S306: Update the text object based on the display content associated with the candidate words, and save the updated text object as a processed text object;

[0150] S307: In response to receiving a target text object acquisition request from the target device, select a target text object from the processed text objects;

[0151] S308: Verify the candidate words contained in the target text object to obtain the verification result;

[0152] S309: Adjust the target text object based on the verification result to obtain the adjusted target text object, and send the adjusted target text object to the target device.

[0153] The second aspect of this disclosure also provides an information processing system, such as... Figure 4 As shown, it includes:

[0154] The first server 401 is used to obtain initial entity words in a text object; in response to the existence of matching information for the initial entity words, the initial entity words are used as candidate words, and the matching content is used as the display content associated with the candidate words, wherein the matching content corresponds to the matching information; the text object is updated based on the display content associated with the candidate words, and the updated text object is saved as a processed text object.

[0155] The first server 401 is used to obtain the sentences contained in the text object; input the sentences into the target model to obtain the sentence recognition result output by the target model; if the type of the entity word contained in the sentence recognition result is a preset type, take the entity word as the initial entity word, and determine the position of the initial entity word in the text object based on the sentence position information of the entity word contained in the sentence recognition result.

[0156] The first server 401 is configured to, based on at least one of the matched content and the candidate words, determine that a preset condition is met, use the matched content as the display content associated with the candidate words in the text object, and set the candidate words in the text object to a first display state.

[0157] The first server 401 is configured to perform at least one of the following:

[0158] If the candidate word is located at a preset position in the text object, the preset condition is determined to be met.

[0159] If there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, then the preset condition is determined to be satisfied.

[0160] If the matched content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than a preset threshold, then the preset condition is satisfied.

[0161] The first server 401 is used to train a first preset model based on a first training sample to obtain a first model; the first training sample is a training sample in a first sample set; the second preset model is trained based on a second training sample and the first model to obtain a trained second preset model, and the trained second preset model is used as the target model; the second training sample is a training sample in a second sample set; the number of training samples in the second sample set is greater than the number of training samples in the first sample set.

[0162] like Figure 5 As shown, the system may further include:

[0163] The target device 501 is used to send a target text object acquisition request to the first server, and to receive and display the target text object sent by the first server.

[0164] The first server 401 is configured to, in response to receiving a target text object acquisition request from the target device, select the target text object from the processed text objects and send the target text object to the target device.

[0165] The target device 501 can be a terminal device used by the user, such as any one of a smartphone, tablet computer, laptop computer, or personal computer.

[0166] The first server 401 is configured to verify the candidate words contained in the target text object and obtain a verification result; adjust the target text object based on the verification result to obtain an adjusted target text object, and send the adjusted target text object to the target device.

[0167] Regarding the operation of the target device 501 on the candidate words contained in the target text object, there are two possible methods, which will be described separately:

[0168] The first method

[0169] The target device 501 is used to obtain display content associated with the target word based on the target word content acquisition request; and to display the display content in a first window; the target word is one of the candidate words contained in the target text object.

[0170] In this approach, the target text object received by the target device can directly contain the display content associated with each candidate word. The target word content retrieval request can be generated when a user clicks on a target word among the candidate words.

[0171] The target device can, upon detecting that a user clicks on any candidate word in the target text object, use that candidate word as the target word and generate a target word content retrieval request; based on the target word content retrieval request, select the display content associated with the target word from all the display content associated with candidate words stored locally; and then add the display content associated with the target word to the first window and display it.

[0172] The size of the first window can be smaller than the display area of ​​the target device; the position of the first window can be at a specified location of the target word, such as above, above right, below right, to the right, below, etc., of the target word. The display state of the first window can be semi-transparent, opaque, etc.

[0173] The second method

[0174] The target device 501 is used to obtain display content associated with the target word based on the target word content acquisition request; and to display the display content in a first window; the target word is one of the candidate words contained in the target text object.

[0175] The target device 501 is used to send the target word content acquisition request to the first server and receive the display content associated with the target word sent by the first server.

[0176] The first server 401 is configured to, in response to receiving a target word content acquisition request from the target device, acquire the display content associated with the target word, and send the display content associated with the target word to the target device.

[0177] In this approach, the target text object received by the target device may not contain display content associated with the candidate words. The target word content retrieval request may be generated when the user clicks on the target word among the candidate words.

[0178] The target device 501 can, upon detecting that a user clicks on any candidate word in the target text object, use that candidate word as the target word and generate a target word content retrieval request; and send the target word content retrieval request to the first server; the first server 401 is configured to, in response to receiving the target word content retrieval request from the target device, retrieve the display content associated with the target word and send the display content associated with the target word to the target device; then, the target device 501 can display the received display content associated with the target word in the first window.

[0179] The size of the first window can be smaller than the display area of ​​the target device; the position of the first window can be at a specified location of the target word, such as above, above right, below right, to the right, below, etc., of the target word. The display state of the first window can be semi-transparent, opaque, etc.

[0180] Furthermore, the system also includes:

[0181] The second server 502 is used to send the target page content to the target device in response to the target page acquisition request sent by the target device;

[0182] The target device 501 is configured to, in response to an operation on the target link in the display content displayed in the first window, send a target page retrieval request to the second server, and receive and display the target page content sent by the second server, when the display content contains a target link.

[0183] Specifically, the displayed content may or may not include a target link. When a user views the displayed content associated with the target keyword in the first window on the target device, if the displayed content contains a target link, the user can decide whether to click the target link to further obtain related content based on their needs. If the user decides to further obtain related content, they can click the target link. Correspondingly, the target device can respond to the operation on the target link in the displayed content in the first window by sending a target page retrieval request to the second server. Then, the second server 502 responds to the target page retrieval request sent by the target device by sending the target page content to the target device. Finally, the target device receives and displays the target page content sent by the second server.

[0184] The second server may be the same as or different from the first server; this is not limited here.

[0185] The content of the target page varies depending on the specific circumstances. For example, if the target keyword is "medicine," the target page content could be an online store where the medicine can be purchased; if the target keyword is "disease," the target page content could be a page listing hospitals that can treat the disease. Further examples are not provided here.

[0186] It should be understood that the processing that the first server provided in the second aspect embodiment can perform is the same as the information processing method of the first aspect embodiment described above, but will not be described in detail.

[0187] By adopting the above scheme, the initial entity words in the text object can be obtained. Then, if there is matching information for the initial entity, the initial entity words are used as candidate words, and the display content of the candidate words is determined. The text object is updated based on the display content associated with the candidate words and saved as a processed text object. Thus, when displaying the processed text object, the content associated with the words in the processed text object can be viewed more efficiently and conveniently, improving the overall efficiency.

[0188] A third aspect of this disclosure provides an information processing apparatus, such as... Figure 6 As shown, it includes:

[0189] Initial processing module 601 is used to obtain the initial entity words in the text object;

[0190] The content processing module 602 is used to respond to the existence of matching information for the initial entity word, to use the initial entity word as a candidate word, and to use the matching content as the display content associated with the candidate word, wherein the matching content corresponds to the matching information;

[0191] Update module 603 is used to update the text object based on the display content associated with the candidate words;

[0192] Storage module 604 is used to save the updated text object as a processed text object.

[0193] The initial processing module 601 is used to obtain the sentences contained in the text object; input the sentences into the target model to obtain the sentence recognition result output by the target model; if the type of the entity word contained in the sentence recognition result is a preset type, use the entity word as the initial entity word, and determine the position of the initial entity word in the text object based on the sentence position information of the entity word contained in the sentence recognition result.

[0194] The content processing module 602 is used to, based on at least one of the matching content and the candidate words, determine that a preset condition is met, to use the matching content as the display content associated with the candidate words in the text object, and to set the candidate words in the text object to a first display state.

[0195] The content processing module 602 is configured to perform at least one of the following:

[0196] If the candidate word is located at a preset position in the text object, the preset condition is determined to be met.

[0197] If there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, then the preset condition is determined to be satisfied.

[0198] If the matched content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than a preset threshold, then the preset condition is satisfied.

[0199] exist Figure 6 On the basis of, such as Figure 7 The apparatus shown also includes:

[0200] Training module 701 is used to train a first preset model based on a first training sample to obtain a first model; the first training sample is a training sample in a first sample set; a second preset model is trained based on a second training sample and the first model to obtain a trained second preset model, and the trained second preset model is used as the target model; the second training sample is a training sample in a second sample set; the number of training samples in the second sample set is greater than the number of training samples in the first sample set.

[0201] The device further includes:

[0202] The communication module 702 is used to receive a target text object acquisition request sent by the target device, and to send the target text object to the target device;

[0203] The selection module 703 is used to select a target text object from the processed text objects in response to the communication module receiving a target text object acquisition request from the target device.

[0204] The device further includes:

[0205] The verification module 704 is used to verify the candidate words contained in the target text object and obtain the verification result; and to adjust the target text object based on the verification result to obtain the adjusted target text object.

[0206] The communication module 702 is used to send the adjusted target text object to the target device.

[0207] The communication module 702 is used to receive a target word content acquisition request sent by the target device, and send the display content associated with the target word to the target device;

[0208] The selection module 703 is used to obtain the display content associated with the target word in response to the target word content acquisition request; wherein the target word is one of the candidate words contained in the target text object.

[0209] It should be understood that the information processing apparatus provided in the third aspect embodiment is capable of performing the same processing as the information processing method in the first aspect embodiment described above, but will not be described in detail.

[0210] By adopting the above scheme, the text object can be processed to obtain candidate words in the sentences. Then, if the candidate words contain matching information, the display content of the candidate words can be determined. The candidate words contained in the text object and their display content are associated and saved as a processed text object. Thus, when displaying the processed text object, the associated content of the words in the processed text object can be viewed more efficiently and conveniently, improving the overall efficiency.

[0211] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0212] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0213] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, first servers, blade first servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0214] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the electronic device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0215] Multiple components in electronic device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows electronic device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0216] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above. For example, in some embodiments, the various methods described above can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the various methods described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the various methods described above by any other suitable means (e.g., by means of firmware).

[0217] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0218] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or a first server.

[0219] In the context of this disclosure, 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. A machine-readable medium 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0220] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0221] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a first data server), or computing systems that include middleware components (e.g., as a first application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0222] A computer system may include a client and a primary server. The client and primary server are generally geographically separated and typically interact via a communication network. The client-primary server relationship is established by computer programs running on the respective computers and having a client-primary server relationship with each other. The primary server may be a cloud primary server, a primary server in a distributed system, or a primary server incorporating blockchain technology.

[0223] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0224] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An information processing method, comprising: The sentences contained in the text object are input into the target model to obtain the sentence recognition results output by the target model; If the entity words in the sentence segmentation recognition result are of a preset type, the entity words are used as initial entity words. Based on the sentence segmentation position information of the entity words in the sentence segmentation recognition result, the position of the initial entity words in the text object is determined. This includes: determining the relative position of the initial entity words in the j-th paragraph based on the sentence segmentation position information of the initial entity words in the i-th sentence recognition result and the j-th paragraph where the i-th sentence is located; i and j are integers greater than or equal to 1; and determining the position of the initial entity words in the text object based on the relative position of the j-th paragraph in the text object and the relative position of the initial entity words in the j-th paragraph. In response to the existence of matching information for the initial entity word, the initial entity word is used as a candidate word. If, based on the matching content and at least one of the candidate words, a preset condition is met, the matching content is used as the display content associated with the candidate word in the text object. The matching content corresponds to the matching information. Determining that the preset condition is met includes: determining that the preset condition is met if the candidate word is located at a preset position in the text object; wherein the preset position does not include the title, summary, or image of the text object. The text object is updated based on the display content associated with the candidate words, and the updated text object is saved as a processed text object. The initial entity words are obtained based on the sentences contained in the text object, including: segmenting the text object to obtain at least one paragraph contained in the text object; and processing the at least one paragraph to obtain multiple sentences contained in the at least one paragraph.

2. The method according to claim 1, wherein, Also includes: If, based on the matched content and at least one of the candidate words, a preset condition is met, the candidate word in the text object is set to a first display state.

3. The method according to claim 2, wherein determining that the preset condition is met further includes at least one of the following: If there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, then the preset condition is determined to be satisfied. If the matched content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than a preset threshold, then the preset condition is satisfied.

4. The method according to any one of claims 1-3, further comprising: The first model is obtained by training the first preset model based on the first training samples; The first training sample is the training sample in the first sample set; The second preset model is trained based on the second training samples and the first model to obtain the trained second preset model, and the trained second preset model is used as the target model; the second training samples are the training samples in the second sample set. The number of training samples in the second sample set is greater than the number of training samples in the first sample set.

5. The method according to claim 4, further comprising: In response to receiving a target text object retrieval request from a target device, a target text object is selected from the processed text objects and sent to the target device.

6. The method according to claim 5, wherein, Sending the target text object to the target device includes: The candidate words contained in the target text object are validated to obtain a validation result; the target text object is adjusted based on the validation result to obtain an adjusted target text object, and the adjusted target text object is sent to the target device.

7. The method according to claim 5, further comprising: In response to receiving a target word content retrieval request from the target device, the display content associated with the target word is retrieved, and the display content associated with the target word is sent to the target device; wherein, the target word is one of the candidate words contained in the target text object.

8. An information processing system, comprising: A first server is used to input sentences contained in a text object into a target model to obtain sentence recognition results output by the target model. If the type of entity words contained in the sentence recognition results is a preset type, the entity words are used as initial entity words. Based on the sentence position information of the entity words contained in the sentence recognition results, the position of the initial entity words in the text object is determined. This includes: based on the sentence position information of the entity words contained in the i-th sentence recognition result and the j-th paragraph where the i-th sentence is located, determining the relative position of the initial entity words in the j-th paragraph; i and j are integers greater than or equal to 1; based on the relative position of the j-th paragraph in the text object and the relative position of the initial entity words in the j-th paragraph, determining... The initial entity word is positioned within the text object. In response to the existence of matching information for the initial entity word, the initial entity word is used as a candidate word. Based on the matching content and at least one of the candidate words, if a preset condition is met, the matching content is used as the display content associated with the candidate word in the text object. The matching content corresponds to the matching information. Determining that the preset condition is met includes: if the candidate word is positioned at a preset location, the preset condition is met. The preset location does not include the title, summary, or image of the text object. The text object is updated based on the display content associated with the candidate word, and the updated text object is saved as a processed text object. The first server is configured to obtain the initial entity word based on the sentences contained in the text object, including: segmenting the text object to obtain at least one paragraph contained in the text object; and processing the at least one paragraph to obtain multiple sentences contained in the at least one paragraph.

9. The system according to claim 8, wherein, The first server is configured to set the candidate word in the text object to a first display state when, based on the matched content and at least one of the candidate words, a preset condition is met.

10. The system according to claim 9, wherein, The first server is configured to perform at least one of the following: If there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, then the preset condition is determined to be satisfied. If the matched content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than a preset threshold, then the preset condition is satisfied.

11. The system according to any one of claims 8-10, wherein, The first server is used to train a first preset model based on a first training sample to obtain a first model; the first training sample is a training sample in a first sample set. The second preset model is trained based on the second training samples and the first model to obtain the trained second preset model, and the trained second preset model is used as the target model; the second training samples are the training samples in the second sample set. The number of training samples in the second sample set is greater than the number of training samples in the first sample set.

12. The system according to claim 11, further comprising: The target device is used to send a target text object acquisition request to the first server, and to receive and display the target text object sent by the first server. The first server is configured to, in response to receiving a target text object retrieval request from the target device, select the target text object from the processed text objects and send the target text object to the target device.

13. The system according to claim 12, wherein, The first server is configured to verify the candidate words contained in the target text object and obtain a verification result; adjust the target text object based on the verification result to obtain an adjusted target text object, and send the adjusted target text object to the target device.

14. The system according to claim 12, wherein, The target device is configured to obtain display content associated with the target word based on a target word content retrieval request; and display the display content in a first window; The target word is one of the candidate words contained in the target text object.

15. The system according to claim 14, wherein, The target device is configured to send a request to the first server to obtain the content of the target word, and to receive the display content associated with the target word from the first server. The first server is configured to, in response to receiving a target word content retrieval request from the target device, retrieve the display content associated with the target word, and send the display content associated with the target word to the target device.

16. The system according to claim 14 or 15, further comprising: The second server is used to send the target page content to the target device in response to the target page retrieval request sent by the target device. The target device is configured to, in response to an operation on the target link in the display content displayed in the first window, send a target page retrieval request to the second server, and receive and display the target page content sent by the second server, when the display content contains a target link.

17. An information processing apparatus, comprising: An initial processing module is used to input the sentences contained in the text object into the target model to obtain the sentence recognition results output by the target model; if the type of the entity words contained in the sentence recognition results is a preset type, the entity words are used as initial entity words, and the position of the initial entity words in the text object is determined based on the sentence position information of the entity words contained in the sentence recognition results. This includes: determining the relative position of the initial entity words in the j-th paragraph based on the sentence position information of the entity words contained in the i-th sentence recognition result and the j-th paragraph in which the i-th sentence is located; i and j are integers greater than or equal to 1; and determining the position of the initial entity words in the text object based on the relative position of the j-th paragraph in the text object and the relative position of the initial entity words in the j-th paragraph. A content processing module is configured to, in response to the existence of matching information for the initial entity word, use the initial entity word as a candidate word, and, based on the matching content and at least one of the candidate words, determine that a preset condition is met, use the matching content as the display content associated with the candidate word in the text object. The matching content corresponds to the matching information. Determining that the preset condition is met includes: determining that the preset condition is met when the position of the candidate word in the text object is a preset position; wherein the preset position does not include the title, summary, and image of the text object. The update module is used to update the text object based on the display content associated with the candidate words; The storage module is used to save the updated text object as a processed text object. The initial processing module is used to obtain the initial entity word based on the sentences contained in the text object, including: segmenting the text object to obtain at least one paragraph contained in the text object; and processing the at least one paragraph to obtain multiple sentences contained in the at least one paragraph.

18. The apparatus according to claim 17, wherein, The content processing module is used to set the candidate word in the text object to a first display state when it is determined that the preset conditions are met based on the matched content and at least one of the candidate words.

19. The apparatus according to claim 18, wherein, The content processing module is configured to perform at least one of the following: If there are other candidate words in the text object that are the same as the candidate word, and the position of the candidate word in the text object is before the other candidate words, then the preset condition is determined to be satisfied. If the matched content contains candidate links and the remaining number of candidate objects associated with the candidate links is greater than a preset threshold, then the preset condition is satisfied.

20. The apparatus according to any one of claims 17-19, further comprising: The training module is used to train the first preset model based on the first training samples to obtain the first model; The first training sample is the training sample in the first sample set; The second preset model is trained based on the second training samples and the first model to obtain the trained second preset model, and the trained second preset model is used as the target model; the second training samples are the training samples in the second sample set. The number of training samples in the second sample set is greater than the number of training samples in the first sample set.

21. The apparatus according to any one of claims 17-19, further comprising: A communication module is used to receive a target text object acquisition request sent by a target device, and to send the target text object to the target device; The selection module is used to select a target text object from the processed text objects in response to the communication module receiving a target text object acquisition request from the target device.

22. The apparatus of claim 21, further comprising: The verification module is used to verify the candidate words contained in the target text object and obtain the verification result; The target text object is adjusted based on the verification result to obtain the adjusted target text object; The communication module is used to send the adjusted target text object to the target device.

23. The apparatus according to claim 22, wherein, The communication module is used to receive a target word content acquisition request sent by the target device, and send the display content associated with the target word to the target device; The selection module is used to obtain the display content associated with the target word in response to the target word content acquisition request; wherein the target word is one of the candidate words contained in the target text object.

24. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

25. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

26. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images