CN116955620A - Text recognition method, device, electronic equipment and storage medium - Google Patents

Abstract

The disclosure provides a text recognition method, a text recognition device, electronic equipment and a storage medium, which can be applied to the technical field of artificial intelligence and the technical field of finance. The method comprises the following steps: identifying text content of a target text to obtain recommendation information of a target product; according to the recommendation information, inquiring the association information corresponding to the target product by calling a third party platform; extracting a target field from the target text under the condition that the association information meets a first preset condition, wherein the target field characterizes the attribute type of the recommendation information; and generating an attribute identification result of the target text according to the proportion of the target field to the text content.

Description

Text recognition method, device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence technology and financial technology, and in particular, to a text recognition method, apparatus, electronic device, and medium.

Background

In the related art, some institutions recommend financial products having abnormal conditions to a subject by using a telecommunication channel. For example, such institutions recommend financial products that have abnormal conditions by publishing text written from the perspective of the product audience.

In the process of implementing the inventive concept of the present disclosure, the inventors found that, in the related art, the accuracy of determining that the recommended text has an abnormal condition is low.

Disclosure of Invention

In view of the foregoing, the present disclosure provides a text recognition method, apparatus, electronic device, and medium.

According to a first aspect of the present disclosure, there is provided a text recognition method, comprising: identifying text content of a target text to obtain recommendation information of a target product; according to the recommendation information, inquiring the association information corresponding to the target product by calling a third party platform; extracting a target field from the target text under the condition that the association information meets a first preset condition, wherein the target field characterizes the attribute type of the recommendation information; and generating an attribute identification result of the target text according to the proportion of the target field to the text content.

According to an embodiment of the present disclosure, extracting a target field from a target text in a case where the association information satisfies a first predetermined condition includes: acquiring a pre-stored text corresponding to a target product, wherein the pre-stored text represents historical recommendation information for recommending the target product; and matching the target text with the pre-stored text, and determining a target field.

According to an embodiment of the present disclosure, the pre-stored text includes a recommended content field and a modifier field; matching the target text with a plurality of pre-stored texts to determine a target field, including: determining a target recommended content field in the target text by matching the text field and the recommended content field in the target text; determining a target modification field in the target text by matching the text field and the modification field in the target text; and obtaining the target field according to the target recommended content field and the target modification field.

According to an embodiment of the present disclosure, the above text recognition method further includes: counting the number of fields corresponding to each recommended content field in the recommended content text; extracting recommended content fields with the number of corresponding fields being greater than or equal to a preset threshold value from the recommended content text to obtain recommended content fields; and generating a pre-stored text according to the predetermined modification field and the recommended content field.

According to an embodiment of the present disclosure, determining a target recommended content field in a target text by matching a text field and a recommended content field in the target text includes: extracting features of the plurality of text fields to obtain a plurality of text field features, wherein the text fields correspond to the text field features one by one; extracting features of a plurality of recommended content fields to obtain a plurality of recommended content field features, wherein the recommended content fields and the recommended content field features are in one-to-one correspondence; determining, for each text field feature of the plurality of text field features, a similarity between the text field feature and each of the plurality of recommended content fields; and determining the text field corresponding to the target text field characteristic as a target recommended content field, wherein the similarity between the target text field characteristic and at least one recommended content field characteristic meets a preset similarity threshold.

According to an embodiment of the present disclosure, generating an attribute identification result of a target text according to a field proportion of the target field to text content, including: determining first duty ratio information according to the field proportion of the target recommended content field to the text content; determining second duty ratio information according to the field proportion of the target modification field to the text content; and generating an attribute identification result of the target text based on the first duty ratio information and the second duty ratio information.

According to an embodiment of the present disclosure, the recommendation information includes product identification information of a target product and organization identification information corresponding to the target product; according to the recommendation information, the related information corresponding to the target product is queried by calling a third party platform, and the method comprises the following steps: and according to the product identification information and the mechanism identification information, inquiring the association information corresponding to the target product by calling a third party platform.

According to an embodiment of the present disclosure, a target text is determined from a plurality of texts corresponding to target object identification information; the text recognition method further comprises the following steps: and generating prompt information corresponding to the target object identification information under the condition that the number of the advertisement texts in the texts is larger than or equal to a second preset threshold value, wherein the advertisement texts are determined according to the attribute identification result.

A second aspect of the present disclosure provides a text recognition apparatus, comprising: the identification module is used for identifying the text content of the target text and obtaining the recommendation information of the target product; the query module is used for querying the association information corresponding to the target product by calling the third-party platform according to the recommendation information; the extraction module is used for extracting a target field from the target text under the condition that the associated information meets a first preset condition, wherein the target field represents the attribute type of the recommended information; the first generation module is used for generating an attribute identification result of the target text according to the field proportion of the target field to the text content.

A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method described above.

A fourth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described method.

According to the text recognition method, the device, the electronic equipment and the medium, the recommendation information of the target product is used for calling the third party platform to inquire the association information corresponding to the target product, so that the abnormal condition of the target product can be determined according to the association information, the accuracy of determining the abnormal condition of the target product recommended by the target text is improved, and the accuracy of determining the abnormal condition of the target text is further improved. And, because the attribute recognition result of the target text is obtained according to the field proportion of the target field to the text content, the accuracy of determining the abnormal condition of the target text is further improved.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario diagram of a text recognition method according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a text recognition method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow chart of a hint information generating method according to an embodiment of the present disclosure;

FIG. 4 schematically illustrates a flow chart of a hint information generating method according to another embodiment of the present disclosure;

FIG. 5 schematically illustrates a block diagram of a text recognition device according to an embodiment of the present disclosure; and

fig. 6 schematically illustrates a block diagram of an electronic device adapted to implement a text recognition method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In the technical scheme of the disclosure, the related data (such as including but not limited to personal information of a user) are collected, stored, used, processed, transmitted, provided, disclosed, applied and the like, all conform to the regulations of related laws and regulations, necessary security measures are adopted, and the public welcome is not violated.

In the process of implementing the inventive concept of the present disclosure, the inventor has found that, in the related art, the accuracy of determining that there is an abnormal condition in a recommended text, which may be a recommended text written from the perspective of a product audience, is low. The recommended text written from the perspective of the product audience may include: the financial products of the XX institution are low in cost and high in income, and the me earns overturned.

Based on the above, the present disclosure provides a text recognition method, which can accurately recognize a recommended text issued on a platform in the presence of an abnormal condition, and further can enable an operation and maintenance mechanism to which the platform belongs to effectively recognize the recommended text in the presence of the abnormal condition, and control the recommended text. Moreover, by using the text recognition method disclosed by the disclosure, the object can be helped to determine whether text content is actually shared with heart or falsified for profit purposes.

In view of this, an embodiment of the present disclosure provides a text recognition method, including: and identifying the text content of the target text to obtain the recommendation information of the target product. And according to the recommendation information, inquiring the association information corresponding to the target product by calling a third-party platform. And extracting a target field from the target text under the condition that the association information meets the first preset condition, wherein the target field characterizes the attribute type of the recommendation information. And generating an attribute identification result of the target text according to the proportion of the target field to the text content.

Fig. 1 schematically illustrates an application scenario diagram of a text recognition method according to an embodiment of the present disclosure.

As shown in fig. 1, an application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is a medium used to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 through the network 104 using at least one of the first terminal device 101, the second terminal device 102, the third terminal device 103, to receive or send messages, etc. Various communication client applications, such as a shopping class application, a web browser application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only) may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.

The first terminal device 101, the second terminal device 102, the third terminal device 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the text recognition method provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the text recognition device provided by the embodiments of the present disclosure may be generally disposed in the server 105. The text recognition method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105. Accordingly, the text recognition apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The text recognition method of the disclosed embodiment will be described in detail below with reference to fig. 2 to 4 based on the scenario described in fig. 1.

Fig. 2 schematically illustrates a flow chart of a text recognition method according to an embodiment of the present disclosure.

As shown in fig. 2, the text recognition method of this embodiment includes operations S210 to S240.

In operation S210, text contents of the target text are recognized, and recommendation information of the target product is obtained.

In operation S220, according to the recommendation information, the association information corresponding to the target product is queried by calling the third party platform.

In operation S230, in case the association information satisfies a first predetermined condition, a target field is extracted from the target text, wherein the target field characterizes an attribute type of the recommended information.

In operation S240, an attribute recognition result of the target text is generated according to the field proportion of the target field to the text content.

According to embodiments of the present disclosure, the target text may be text to be identified. The text may include: text published on a public platform, and the like.

According to embodiments of the present disclosure, the target product may be a product involved in the target text. The product can comprise financial products, physical products and the like.

According to an embodiment of the present disclosure, the recommendation information may be description information about the target product in the target text. The recommendation information may include product identification information of the target product.

According to embodiments of the present disclosure, the third party platform may be a platform for querying association information of the target product. The associated information may be queried description information about the target product, etc. The associated information may include qualification information of the institution to which the target product belongs, etc.

According to an embodiment of the present disclosure, the first predetermined condition may be a condition that determines whether the target product meets the demand.

For example: under the condition that the information quantity of the related information obtained by inquiry is smaller than a preset threshold value, the related information can be determined to not meet a first preset condition; when the information amount of the searched association information is equal to or greater than the predetermined threshold value, it may be determined that the association information satisfies the first predetermined condition.

Also for example: the mechanism qualification information and the pre-stored mechanism qualification information can be compared, and under the condition that the comparison results are consistent, the mechanism qualification information can be determined to meet the first preset condition; and under the condition that the comparison results are inconsistent, determining that the establishment qualification information does not meet the first preset condition.

Also for example: the association information may further include product standard information, and the queried product standard information may be matched with pre-stored product standard information to determine whether the target product meets a standard, where the product standard information may include a target compliance identifier corresponding to the target product, and the pre-stored product standard information may include pre-stored compliance identifiers corresponding to multiple products, respectively. Under the condition that the pre-stored compliance identifications corresponding to the various products respectively comprise target compliance identifications, determining that the product standard information meets a first preset condition; in the case that the pre-stored compliance identification corresponding to each of the plurality of products does not include the target compliance identification, it may be determined that the product standard information does not satisfy the first predetermined condition.

According to embodiments of the present disclosure, the target field may include a content field or the like corresponding to the target product. The attribute type of the recommendation information may include a share type and an advertisement type. The recommendation information of the sharing type can be recommendation information for objectively evaluating the target product, such as 'product is relatively stable', and 'product is relatively suitable for long-term attention', etc.; the recommendation information of the advertisement type may be recommendation information including more subjective content, such as "super good" and the like.

According to an embodiment of the present disclosure, the attribute identification result may include a first result and a second result. The first result may characterize the target text as advertisement text and the second result may characterize the target text as shared text.

According to the embodiment of the disclosure, the text content of the target text can be processed by using the trained model, and information such as product identification information of the target product can be obtained.

According to the embodiment of the disclosure, the related information about the target product can be queried through the third party platform according to the product identification information of the target product.

According to the embodiment of the disclosure, under the condition that the association information meets the first preset condition, the probability of the abnormal condition of the target product can be determined to be high, the target text can be processed by using the trained model, the target field is obtained, and then the attribute recognition result of the target text is generated according to the field proportion of the target field to the text content.

A first result may be generated if the proportion of the target field to the text content is greater than or equal to a predetermined threshold; the second result may be generated in case the proportion of the target field to the field of the text content is less than a predetermined threshold.

Under the condition that the attribute identification result corresponding to the target text is a first result, the target text can be determined to be the text of the advertisement type with abnormal conditions; in the case where the attribute recognition result corresponding to the target text is the second result, it may be determined that the target text does not have an abnormal condition.

According to the embodiment of the disclosure, the recommendation information of the target product is used to call the third party platform to query the association information corresponding to the target product, so that the abnormal condition of the target product can be determined according to the association information, the accuracy of determining the abnormal condition of the target product recommended by the target text is improved, and the accuracy of determining the abnormal condition of the target text is further improved. And, because the attribute recognition result of the target text is obtained according to the field proportion of the target field to the text content, the accuracy of determining the abnormal condition of the target text is further improved.

According to an embodiment of the present disclosure, extracting a target field from a target text in a case where the association information satisfies a first predetermined condition includes: and acquiring a pre-stored text corresponding to the target product, wherein the pre-stored text represents historical recommendation information for recommending the target product. And matching the target text with the pre-stored text, and determining a target field.

According to embodiments of the present disclosure, the pre-stored text may include pre-stored advertisement type text and pre-stored non-advertisement type text.

According to embodiments of the present disclosure, pre-stored advertisement type text may be matched with target text to determine a first repetition field included in the target text with the advertisement type text. And/or the pre-stored non-advertising type text may be matched with the target text to determine a second repetition field included with the target text between the pre-stored advertising text and the pre-stored non-advertising type text. The first repetition field and the second repetition field may each be a target field. The first repeated field and the second repeated field may be fields in which the similarity between the target text and the pre-stored text is greater than or equal to a predetermined similarity threshold. The predetermined similarity threshold may be 70%,80%, 90%, etc.

According to the embodiment of the disclosure, the target field is determined by matching the target text with the pre-stored text, so that the accuracy of the determined target field is improved.

According to an embodiment of the present disclosure, the pre-stored text includes a recommended content field and a modifier field. Matching the target text with a plurality of pre-stored texts to determine a target field, including: and determining the target recommended content field in the target text by matching the text field and the recommended content field in the target text. And determining the target modifier field in the target text by matching the text field and the modifier field in the target text. And obtaining the target field according to the target recommended content field and the target modification field.

According to embodiments of the present disclosure, the recommended content field may be a field that sets forth characteristics of the target product. For example: the fields such as "can help" and "functions" are divided together.

According to embodiments of the present disclosure, the modifier field may be a field that subjectively describes the target product. For example: "at one go", "without any" "super simple".

According to the embodiment of the present disclosure, the similarity between the text field and the recommended content field may be determined, and thus, the text field having the similarity with the recommended content field equal to or greater than a predetermined similarity threshold may be determined as the target recommended content field. The predetermined similarity threshold may be 70%,80%, 90%, etc.

According to the embodiment of the present disclosure, the similarity between the text field and the modifier field may be determined, and thus, the text field having the similarity with the modifier field equal to or greater than a predetermined similarity threshold may be determined as the target modifier field. The predetermined similarity threshold may be 70%,80%, 90%, etc.

According to embodiments of the present disclosure, the determined target recommended content field and target modifier field may be taken as target fields.

According to the embodiment of the disclosure, the accuracy of determining the target recommended content field in the target text is improved by matching the text field in the target text with the recommended content field, and the accuracy of determining the target modification field in the target text is improved by matching the text field in the target text with the modification field, and based on this, the accuracy of determining the target modification field is further improved.

According to embodiments of the present disclosure, the target text may be processed using a recommended content recognition model to determine target recommended content fields. The recommended content recognition model may be obtained by training an ERNIE (Enhanced Representation through kNowledge IntEgration, enhanced characterization by knowledge integration) model using a first training text data set to obtain a trained first initial model, hierarchically connecting the trained first initial model with a CNN (Convolutional Neural Networks, convolutional neural network) model to obtain a first intermediate model, and then training the first intermediate model using a first test text data set.

According to embodiments of the present disclosure, the target modifier field may be processed using a modifier content identification model. The ERNIE model may be trained by using a second training text data set to obtain a trained second initial model, and the trained second initial model is hierarchically connected to the CNN model to obtain a second intermediate model, and the second intermediate model may be trained by using a second test text data set, thereby the modified content recognition model may be obtained.

According to an embodiment of the present disclosure, the above text recognition method further includes: and counting the number of fields corresponding to each recommended content field in the recommended content text. And extracting the recommended content fields with the number of the corresponding fields being greater than or equal to a preset threshold value from the recommended content text to obtain the recommended content fields. And generating a pre-stored text according to the predetermined modification field and the recommended content field.

According to an embodiment of the present disclosure, a recommended content field having a corresponding number of fields equal to or greater than a predetermined threshold may be extracted from a plurality of recommended content texts using an STC (suffix tree clustering, suffix tree) algorithm. The predetermined threshold may be determined on demand, and the disclosure is not limited herein.

According to the embodiment of the disclosure, since the recommended content fields with the number of the corresponding fields being greater than or equal to the predetermined threshold value are extracted from the recommended content text, the target recommended content field is determined through the recommended content field, and the accuracy of the determined target recommended content field is improved.

According to an embodiment of the present disclosure, determining a target recommended content field in a target text by matching a text field and a recommended content field in the target text includes: and extracting the characteristics of the plurality of text fields to obtain a plurality of text field characteristics, wherein the text fields are in one-to-one correspondence with the text field characteristics. And extracting features of the plurality of recommended content fields to obtain a plurality of recommended content field features, wherein the plurality of recommended content fields and the plurality of recommended content field features are in one-to-one correspondence. For each text field feature of the plurality of text field features, a similarity between the text field feature and each of the plurality of recommended content fields is determined. And determining the text field corresponding to the target text field characteristic as a target recommended content field, wherein the similarity between the target text field characteristic and at least one recommended content field characteristic meets a preset similarity threshold.

According to embodiments of the present disclosure, text fields may be processed using a trained model to obtain a plurality of text field features; and, the recommended content fields may be processed using the trained model to obtain a plurality of recommended content field features.

According to an embodiment of the present disclosure, the plurality of text field features may include a text field feature A1 and a text field feature A2; the plurality of recommended content field features may include a recommended content field feature B1 and a recommended content field feature B2. A similarity 11 between the text field feature A1 and the recommended content field feature B1 may be determined; a similarity 21 between the text field feature A2 and the recommended content field feature B1 may be determined; a similarity 12 between the text field feature A1 and the recommended content field feature B2 may be determined; a similarity 22 between the text field feature A2 and the recommended content field feature B2 may be determined.

Under the condition that at least one of the similarity 11 and the similarity 12 is larger than or equal to a preset similarity threshold value, determining a text field corresponding to the text field characteristic A1 as a target recommended content field; in the case where at least one of the similarity 21 and the similarity 22 is equal to or greater than a predetermined similarity threshold, it may be determined that the text field corresponding to the text field feature A2 is the target recommended content field. Wherein the predetermined similarity threshold may be 70%,80% or 90%.

According to the embodiment of the disclosure, the similarity between the text field feature and each of the plurality of recommended content field features is determined for each of the plurality of text field features, so that the accurate target text field feature can be determined, and then the text field corresponding to the target text field feature is determined as the target recommended content field, so that the accuracy of determining the target recommended content field is improved.

According to an embodiment of the present disclosure, determining a target modifier field in a target text by matching a text field and a modifier field in the target text includes: and extracting the characteristics of the plurality of text fields to obtain a plurality of text field characteristics, wherein the text fields are in one-to-one correspondence with the text field characteristics. And extracting the characteristics of the plurality of modification fields to obtain a plurality of modification field characteristics, wherein the plurality of modification fields are in one-to-one correspondence with the plurality of modification field characteristics. For each text field feature of the plurality of text field features, a similarity between the text field feature and each of the plurality of modifier fields is determined. And determining the text field corresponding to the target text field characteristic as a target modifier field, wherein the similarity between the target text field characteristic and at least one modifier field characteristic respectively meets a preset similarity threshold.

According to embodiments of the present disclosure, text fields may be processed using a trained model to obtain a plurality of text field features; and, the modifier field may be processed using the trained model to obtain a plurality of modifier field features.

According to an embodiment of the present disclosure, the plurality of text field features may include text field feature C3 and text field feature C4; the plurality of modifier field features may include a modifier field feature D3 and a modifier field feature D4. A similarity 33 between the text field feature C3 and the modifier field feature D3 may be determined; a similarity 43 between the text field feature C4 and the modifier field feature D3 may be determined; a similarity 34 between the text field feature C3 and the modifier field feature D4 may be determined; a similarity 44 between the text field feature C4 and the modifier field feature D4 may be determined.

In the case that at least one of the similarity 33 and the similarity 34 is greater than or equal to a predetermined similarity threshold, it may be determined that the text field corresponding to the text field feature C3 is a target modifier field; in the case where at least one of the similarity 43 and the similarity 44 is equal to or greater than the predetermined similarity threshold, it may be determined that the text field corresponding to the text field feature C4 is the target modifier field. Wherein the predetermined similarity threshold may be 70%,80% or 90%.

According to the embodiment of the disclosure, the similarity between the text field feature and each of the plurality of modification field features is determined for each of the plurality of text field features, so that the accurate target text field feature can be determined, and then the text field corresponding to the target text field feature is determined as the target modification field, so that the accuracy of determining the target modification field is improved.

According to an embodiment of the present disclosure, generating an attribute identification result of a target text according to a field proportion of the target field to text content, including: and determining the first duty ratio information according to the field proportion of the target recommended content field to the text content. And determining second duty ratio information according to the field proportion of the target modification field to the text content. And generating an attribute identification result of the target text based on the first duty ratio information and the second duty ratio information.

According to an embodiment of the present disclosure, the target recommended content field may be 3, and the text content may include 10 total fields, and thus, the first duty information may be 30%. The target modifier field may be 4, and thus, the second duty information may be 40%.

According to an embodiment of the present disclosure, the first result may be generated when at least one of the first duty ratio information and the second duty ratio information is equal to or greater than a predetermined duty ratio threshold value corresponding to each; the second result may be generated in a case where both the first and second duty ratio information are smaller than respective corresponding predetermined duty ratio thresholds. The predetermined duty ratio threshold value corresponding to the first duty ratio information may be 70%,80% or 90%. The predetermined duty ratio threshold value corresponding to the second duty ratio information may be 70%,80% or 90%.

According to the embodiment of the disclosure, by generating the attribute identification result of the target text according to the first duty ratio information and the second duty ratio information, compared with generating the attribute identification result according to the duty ratio information of a single dimension, the accuracy of the generated attribute identification result is improved.

According to an embodiment of the present disclosure, the recommendation information includes product identification information of the target product and organization identification information corresponding to the target product. According to the recommendation information, the related information corresponding to the target product is queried by calling a third party platform, and the method comprises the following steps: and according to the product identification information and the mechanism identification information, inquiring the association information corresponding to the target product by calling a third party platform.

According to an embodiment of the present disclosure, the organization identification information may be identification information corresponding to a production organization of the target product. The target text may be processed using the trained model to obtain the facility identification information.

According to the embodiment of the disclosure, the related information corresponding to the XX product of the XX mechanism can be queried according to the XX mechanism and the XX product by calling a third party platform. Where "XX institution" may be institution identification information and "XX product" may be product identification information.

According to the embodiment of the disclosure, by inquiring the association information according to the product identification information and the organization identification information, the accuracy of the association information obtained by inquiry is improved compared with the case that the association information is inquired according to the product identification information only.

According to an embodiment of the present disclosure, the target text is determined from a plurality of texts corresponding to the target object identification information. The text recognition method further comprises the following steps: and generating prompt information corresponding to the object identification information under the condition that the number of the advertisement texts in the plurality of texts is larger than or equal to a second preset threshold value, wherein the advertisement texts are determined according to the attribute identification result.

According to embodiments of the present disclosure, the plurality of texts may be published to the platform by the object by using the target object identification information. Thus, each of the plurality of texts corresponding to the target object identification information can be identified, and the attribute identification result corresponding to each of the plurality of texts can be obtained. Thereby, the advertisement text among the plurality of texts can be determined.

In the case where the number of advertisement texts is equal to or greater than the second predetermined threshold value, it may be determined that the target object identification information has an abnormal condition, based on which the hint information corresponding to the target object identification information may be generated. The prompt information can be used for prompting the abnormal condition of the target object identification information. The second predetermined threshold may be set as desired, and the disclosure is not limited herein.

According to the embodiment of the disclosure, more accurate prompt information can be generated according to the number of advertisement texts in a plurality of texts.

According to an embodiment of the present disclosure, the target text is determined from a plurality of texts corresponding to the target object identification information. The text recognition method further comprises the following steps: and generating prompt information corresponding to the object identification information under the condition that the text proportion of the advertisement text to the plurality of texts is greater than or equal to a third preset threshold value, wherein the advertisement text is determined according to the attribute identification result. The third predetermined threshold may be set as desired, and the disclosure is not limited herein.

According to the embodiment of the disclosure, in the case that the text proportion of the advertisement text to the plurality of texts is greater than or equal to the third predetermined threshold, it may be determined that the abnormal condition exists in the target object identification information, based on which the prompt information corresponding to the target object identification information may be generated. The prompt information can be used for prompting the abnormal condition of the target object identification information.

According to the embodiment of the disclosure, more accurate prompt information can be generated according to the proportion of advertisement texts in a plurality of texts.

Fig. 3 schematically illustrates a flowchart of a hint information generating method according to an embodiment of the present disclosure.

As shown in fig. 3, the hint information generating method of the embodiment includes operations S301 to S309.

In operation S301, a target text is determined from among a plurality of texts corresponding to target object identification information.

In operation S302, text contents of the target text are identified, and recommendation information of the target product is obtained.

In operation S303, according to the recommendation information, the association information corresponding to the target product is queried by calling the third party platform.

In operation S304, in case that the association information satisfies a first predetermined condition, a pre-stored text corresponding to the target product is acquired, wherein the pre-stored text includes a recommended content field and a decoration field.

In operation S305, a target recommended content field in the target text is determined by matching the text field and the recommended content field in the target text.

In operation S306, a target modifier field in the target text is determined by matching the text field and the modifier field in the target text.

In operation S307, a target field is obtained from the target recommended content field and the target modifier field.

In operation S308, an attribute recognition result of the target text is generated according to the field proportion of the target field to the text content.

In operation S309, in case that the number of advertisement texts among the plurality of texts is equal to or greater than the second predetermined threshold value, a hint information corresponding to the object identification information is generated, wherein the advertisement texts are determined according to the attribute recognition result.

Fig. 4 schematically illustrates a flowchart of a hint information generating method according to another embodiment of the present disclosure.

As shown in fig. 4, the hint information generating method of the embodiment includes operations S401 to S412.

In operation S401, a target text is determined from among a plurality of texts corresponding to target object identification information.

In operation S402, text contents of a target text are identified, and recommendation information of a target product is obtained.

In operation S403, according to the recommendation information, the association information corresponding to the target product is queried by calling the third party platform.

In operation S404, the number of fields corresponding to each recommended content field in the recommended content text is counted.

In operation S405, recommended content fields, the number of which is greater than or equal to a predetermined threshold, are extracted from the recommended content text, and the recommended content fields are obtained.

In operation S406, a pre-stored text is generated according to the predetermined modifier field and the recommended content field.

In operation S407, a pre-stored text corresponding to the target product is acquired, wherein the pre-stored text includes a recommended content field and a decoration field.

In operation S408, a target recommended content field in the target text is determined by matching the text field and the recommended content field in the target text.

In operation S409, a target modifier field in the target text is determined by matching the text field and the modifier field in the target text.

In operation S410, a target field is obtained from the target recommended content field and the target modifier field.

In operation S411, an attribute recognition result of the target text is generated according to the field proportion of the target field to the text content.

In operation S412, in case that the number of advertisement texts among the plurality of texts is equal to or greater than a second predetermined threshold value, a hint information corresponding to the object identification information is generated, wherein the advertisement texts are determined according to the attribute recognition result.

Based on the text recognition method, the disclosure also provides a text recognition device. The device will be described in detail below in connection with fig. 5.

Fig. 5 schematically shows a block diagram of a text recognition device according to an embodiment of the present disclosure.

As shown in fig. 5, the text recognition apparatus 500 of this embodiment includes a recognition module 510, a query module 520, an extraction module 530, and a first generation module 540.

The recognition module 510 is configured to recognize text content of the target text, and obtain recommendation information of the target product. In an embodiment, the identification module 510 may be configured to perform the operation S210 described above, which is not described herein.

The query module 520 is configured to query, according to the recommendation information, association information corresponding to the target product by calling the third party platform. In an embodiment, the query module 520 may be configured to perform the operation S220 described above, which is not described herein.

The extracting module 530 is configured to extract a target field from the target text, where the target field characterizes an attribute type of the recommendation information, if the association information satisfies a first predetermined condition. In an embodiment, the extracting module 530 may be configured to perform the operation S230 described above, which is not described herein.

The first generating module 540 is configured to generate an attribute identification result of the target text according to a field proportion of the target field to the text content. In an embodiment, the first generating module 540 may be used to perform the operation S240 described above, which is not described herein.

According to an embodiment of the present disclosure, the extraction module 530 includes an acquisition sub-module and a matching sub-module. The acquisition sub-module is used for acquiring a pre-stored text corresponding to the target product, wherein the pre-stored text represents historical recommendation information for recommending the target product; the matching submodule is used for matching the target text with the prestored text and determining a target field.

According to an embodiment of the present disclosure, a matching submodule includes a first matching unit, a second matching unit, and an obtaining unit. The first matching unit is used for determining a target recommended content field in the target text by matching the text field in the target text with the recommended content field; the second matching unit is used for determining a target modification field in the target text by matching the text field and the modification field in the target text; the acquisition unit is used for acquiring a target field according to the target recommended content field and the target modification field.

According to an embodiment of the present disclosure, the matching submodule further includes a statistics unit, an extraction unit, and a generation unit. The statistics unit is used for counting the number of fields corresponding to each recommended content field in the recommended content text; the extraction unit is used for extracting the recommended content fields with the number of the corresponding fields being more than or equal to a preset threshold value from the recommended content text to obtain recommended content fields; the generation unit is used for generating a pre-stored text according to the predetermined modification field and the recommended content field.

According to an embodiment of the present disclosure, the first matching unit includes a first extraction subunit, a second extraction subunit, a first determination subunit, and a second determination subunit. The first extraction subunit is used for extracting features of a plurality of text fields to obtain a plurality of text field features, wherein the text fields are in one-to-one correspondence with the text field features; the second extraction subunit is used for extracting features of the plurality of recommended content fields to obtain a plurality of recommended content field features, wherein the plurality of recommended content fields are in one-to-one correspondence with the plurality of recommended content field features; the first determining subunit is configured to determine, for each text field feature of the plurality of text field features, a similarity between the text field feature and each of the plurality of recommended content fields; the second determining subunit is configured to determine a text field corresponding to the target text field feature as a target recommended content field, where a similarity between the target text field feature and each of the at least one recommended content field feature meets a predetermined similarity threshold.

According to an embodiment of the present disclosure, the first generation module 540 includes a first determination sub-module, a second determination sub-module, and a generation sub-module. The first determination submodule is used for determining first duty ratio information according to the field proportion of the target recommended content field to the text content; the second determining submodule is used for determining second duty ratio information according to the field proportion of the target modification field to the text content; the generation submodule is used for generating an attribute identification result of the target text based on the first duty ratio information and the second duty ratio information.

According to an embodiment of the present disclosure, the query module 520 includes a query sub-module. The inquiring sub-module is used for inquiring the associated information corresponding to the target product by calling the third-party platform according to the product identification information and the mechanism identification information.

According to an embodiment of the present disclosure, the text recognition apparatus further includes a second generation module. The second generation module is used for generating prompt information corresponding to the target object identification information under the condition that the number of the advertisement texts in the texts is larger than or equal to a second preset threshold value, wherein the advertisement texts are determined according to the attribute identification result.

Any of the plurality of modules of the recognition module 510, the query module 520, the extraction module 530, and the first generation module 540 may be combined in one module to be implemented, or any of the plurality of modules may be split into a plurality of modules, according to embodiments of the present disclosure. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. At least one of the identification module 510, the query module 520, the extraction module 530, and the first generation module 540 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable way of integrating or packaging circuitry, or in any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, at least one of the identification module 510, the query module 520, the extraction module 530, and the first generation module 540 may be at least partially implemented as a computer program module, which when executed, may perform the corresponding functions.

Fig. 6 schematically illustrates a block diagram of an electronic device adapted to implement a text recognition method according to an embodiment of the present disclosure.

As shown in fig. 6, an electronic device 600 according to an embodiment of the present disclosure includes a processor 601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. The processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. Processor 601 may also include on-board memory for caching purposes. The processor 601 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.

In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The processor 601 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 602 and/or the RAM 603. Note that the program may be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 600 may also include an input/output (I/O) interface 605, the input/output (I/O) interface 605 also being connected to the bus 604. The electronic device 600 may also include one or more of the following components connected to an input/output (I/O) interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to an input/output (I/O) interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 602 and/or RAM 603 and/or one or more memories other than ROM 602 and RAM 603 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code means for causing a computer system to carry out the text recognition method provided by the embodiments of the present disclosure when the computer program product is run on the computer system.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 601. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and/or installed from the removable medium 611. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 601. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

It should be noted that, unless there is an execution sequence between different operations or an execution sequence between different operations in technical implementation, the execution sequence between multiple operations may be different, and multiple operations may also be executed simultaneously in the embodiment of the disclosure.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims (11)

1. A text recognition method, comprising:

identifying text content of a target text to obtain recommendation information of a target product;

according to the recommendation information, inquiring the association information corresponding to the target product by calling a third party platform;

extracting a target field from the target text under the condition that the association information meets a first preset condition, wherein the target field characterizes the attribute type of the recommendation information;

and generating an attribute identification result of the target text according to the proportion of the target field to the field of the text content.

2. The method of claim 1, wherein the extracting the target field from the target text if the association information satisfies a first predetermined condition comprises:

acquiring a pre-stored text corresponding to the target product, wherein the pre-stored text represents historical recommendation information for recommending the target product;

and matching the target text with the pre-stored text, and determining the target field.

3. The method of claim 2, wherein the pre-stored text includes a recommended content field and a modifier field;

the matching the target text with a plurality of pre-stored texts, and determining the target field comprises the following steps:

Determining a target recommended content field in the target text by matching a text field in the target text with the recommended content field;

determining a target modifier field in the target text by matching a text field in the target text with the modifier field;

and obtaining the target field according to the target recommended content field and the target modification field.

4. A method according to claim 3, further comprising:

counting the number of fields corresponding to each recommended content field in the recommended content text;

extracting recommended content fields with the number of corresponding fields being greater than or equal to a preset threshold value from the recommended content text to obtain the recommended content fields;

and generating the pre-stored text according to the predetermined modification field and the recommended content field.

5. The method of claim 3, wherein the determining the target recommended content field in the target text by matching the text field in the target text with the recommended content field comprises:

extracting features of a plurality of text fields to obtain a plurality of text field features, wherein the text fields are in one-to-one correspondence with the text field features;

Extracting features of a plurality of recommended content fields to obtain a plurality of recommended content field features, wherein the recommended content fields and the recommended content field features are in one-to-one correspondence;

determining, for each text field feature of the plurality of text field features, a similarity between the text field feature and each of the plurality of recommended content fields;

and determining a text field corresponding to a target text field characteristic as the target recommended content field, wherein the similarity between the target text field characteristic and at least one recommended content field characteristic meets a preset similarity threshold.

6. The method of claim 3, wherein the generating the attribute identification result of the target text according to the field proportion of the target field to the text content comprises:

determining first duty ratio information according to the proportion of the target recommended content field to the text content field;

determining second duty ratio information according to the field proportion of the target modification field to the text content;

and generating an attribute identification result of the target text based on the first duty ratio information and the second duty ratio information.

7. The method according to any one of claims 1 to 6, wherein the recommendation information includes product identification information of the target product and institution identification information corresponding to the target product;

and according to the recommendation information, inquiring the association information corresponding to the target product by calling a third party platform, wherein the method comprises the following steps:

and according to the product identification information and the mechanism identification information, inquiring the association information corresponding to the target product by calling a third party platform.

8. The method of any of claims 1-6, wherein the target text is determined from a plurality of texts corresponding to target object identification information;

the method further comprises the steps of:

and generating prompt information corresponding to the target object identification information under the condition that the number of the advertisement texts in the texts is larger than or equal to a second preset threshold value, wherein the advertisement texts are determined according to the attribute identification result.

9. A text recognition device, comprising:

the identification module is used for identifying the text content of the target text and obtaining the recommendation information of the target product;

the query module is used for querying the association information corresponding to the target product by calling a third party platform according to the recommendation information;

The extraction module is used for extracting a target field from the target text under the condition that the association information meets a first preset condition, wherein the target field characterizes the attribute type of the recommendation information;

the first generation module is used for generating an attribute identification result of the target text according to the proportion of the target field to the text content.

10. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-8.

11. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1-8.