WO2019085856A1

WO2019085856A1 - Text resource push method and apparatus, storage medium, and processor

Info

Publication number: WO2019085856A1
Application number: PCT/CN2018/112379
Authority: WO
Inventors: 石鹏; 王福伟
Original assignee: 北京国双科技有限公司
Priority date: 2017-10-31
Filing date: 2018-10-29
Publication date: 2019-05-09
Also published as: CN109729126A

Abstract

The present application provides a text resource push method and apparatus, a storage medium, and a processor. The method comprises: determining the target text type of a first text obtained by a client; searching for multiple second texts whose types are the target text type in a preset text set; determining first similarities between the first text and the multiple second texts; determining second texts whose first similarities satisfy preset conditions, as target texts; and pushing the target texts to the client. By using the technical solution, the problem in the related art of the low push efficiency of text resources is resolved, thereby improving the push efficiency of the text resources.

Description

Text resource pushing method, device, storage medium and processor

The present application is based on a Chinese patent application filed on Jan. 31, 2017, the entire disclosure of which is hereby incorporated by reference.

Technical field

The present application relates to the field of communications, and in particular, to a method, an apparatus, a storage medium, and a processor for pushing a text resource.

Background technique

With the rapid development of Internet technology, the network is full of text resources. Sometimes, users may need to find relevant information to browse, and how to push relevant text resources for users has become the focus of current research. However, the existing text resource push method is relatively low in relevance and effectiveness, which leads to low efficiency of text resource push.

There is currently no effective solution to the problem of low push efficiency of text resources in related technologies.

Summary of the invention

The embodiment of the present application provides a method, an apparatus, a storage medium, and a processor for pushing a text resource, so as to at least solve the problem that the push efficiency of the text resource in the related art is low.

According to an embodiment of the present application, a method for pushing a text resource is provided, including: determining a target text type of a first text acquired by a client; and searching for a type of the target text type in a preset text set. a second text; determining a first similarity between the first text and the plurality of second texts; determining that the second text whose first similarity satisfies a preset condition is a target text; The text is pushed to the client.

Optionally, determining the first similarity between the first text and the plurality of second texts comprises: dividing the first text according to a plurality of first keywords to obtain a first text block a set, wherein the first keyword is used to indicate a feature of a text segment, the first keyword is in one-to-one correspondence with a first text block in the first set of text blocks, and the first keyword is Corresponding to a second target block in each of the second texts; determining a first target similarity between the first text block and the second text block corresponding to each of the first keywords; The first preset weight corresponding to the first target similarity and the first target similarity determine the first similarity.

Optionally, determining, according to the first preset weight corresponding to each of the first target similarities, the first similarity, the first similarity includes one of: determining according to the first preset weight a first weighted sum of the first target similarity, using the first weighted sum as the first similarity; determining a first weighted average of the first target similarity according to the first preset weight Determining, by the first weighted average, the second similarity; determining a second target similarity between the first text and the second text; according to the first preset weight and the first a second predetermined weight corresponding to the two target similarities determines a second weighted sum of the first target similarity and the second target similarity, and the second weighted sum is used as the first similarity; Determining a second target similarity between the first text and the second text; determining the first target similarity according to the first preset weight and the second preset weight corresponding to the second target similarity a second weighted flat with the second target similarity Number, the second weighted average as the first similarity.

Optionally, determining that the second text that the first similarity meets the preset condition is the target text includes one of: determining that the second text that the first similarity falls within a preset threshold range is Target text; sorting the second text according to the first similarity from high to low; determining that the second predetermined number of the second text is the target text.

Optionally, determining the target text type of the first text acquired by the client comprises: searching for a paragraph in which the second keyword is located in the first text, and determining the found paragraph as a feature paragraph; obtaining a third keyword in the feature paragraph; searching for the target text type corresponding to the third keyword from a correspondence between a keyword and a text type.

According to another embodiment of the present application, there is provided a text resource pushing apparatus, comprising: a first determining module configured to determine a target text type of a first text acquired by a client; a lookup module configured to be in advance Locating a plurality of second texts of the type of the target text type in the set of texts; the second determining module is configured to determine a first similarity between the first text and the plurality of second texts; The third determining module is configured to determine that the second text whose first similarity satisfies the preset condition is the target text; and the pushing module is configured to push the target text to the client.

Optionally, the second determining module includes: a dividing unit, configured to divide the first text according to the multiple first keywords to obtain a first text block set, where the first keyword is used And indicating a feature of the text paragraph, the first keyword is in one-to-one correspondence with the first text block in the first text block set, and the first keyword and the second of each of the second texts a first one of the text blocks; the first determining unit is configured to determine a first target similarity between the first text block and the second text block corresponding to each of the first keywords; and the second determining unit is configured The first similarity is determined according to the first preset weight corresponding to each of the first target similarities and the first target similarity.

Optionally, the first determining module includes: a first searching unit, configured to search for a paragraph in which the second keyword is located in the first text, and determine the found paragraph as a feature paragraph; a unit, configured to obtain a third keyword in the feature paragraph; and a second search unit configured to search for the target text type corresponding to the third keyword from a correspondence between a keyword and a text type.

According to still another embodiment of the present application, there is also provided a storage medium comprising a stored program, wherein the program is executed to perform the method of any of the above.

According to still another embodiment of the present application, there is also provided a processor for running a program, wherein the program is executed to perform the method of any of the above.

Through the application, determining a target text type of the first text acquired by the client; searching for a plurality of second texts of the target text type in the preset text collection; determining between the first text and the plurality of second texts a first similarity; determining that the second text whose first similarity satisfies the preset condition is the target text; and pushing the target text to the client, thereby showing that the target text type of the first text obtained is preset according to the obtained scheme Searching for a plurality of second texts of the same type as the first text, thereby ensuring that the pushed text resource is the same type of text resource as the text that the user desires to find, and then obtaining and searching from the plurality of second texts found. The second text with the higher similarity of the first text is used as the target text, and the target text is pushed to the client, so that the text resource of the pushed client has the same text type and the same as the first text obtained from the client, and is improved. The relevance and effectiveness of pushing text resources to the client, thus improving the efficiency of pushing text resources, thereby solving the phase The problem of low efficiency of pushing text resources in technology.

DRAWINGS

The drawings described herein are intended to provide a further understanding of the present application, and are intended to be a part of this application. In the drawing:

1 is a block diagram showing the hardware structure of a mobile terminal for pushing a text resource according to an embodiment of the present application;

2 is a flowchart of a method for pushing a text resource according to an embodiment of the present application;

3 is a schematic diagram of determining a first similarity according to an alternative embodiment of the present application;

4 is a structural block diagram 1 of a text resource pushing apparatus according to an embodiment of the present application;

FIG. 5 is a structural block diagram 2 of a text resource pushing apparatus according to an embodiment of the present application; FIG.

FIG. 6 is a structural block diagram 3 of a text resource pushing apparatus according to an embodiment of the present application.

Detailed ways

The present application will be described in detail below with reference to the drawings in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.

It is to be understood that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or order.

The method embodiment provided by Embodiment 1 of the present application can be executed in a mobile terminal, a computer terminal or the like. 1 is a block diagram of a hardware structure of a mobile terminal for pushing a text resource according to an embodiment of the present application. As shown in FIG. 1, the mobile terminal 10 may include one or more (in the figure). Only one processor 102 is shown (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. . It will be understood by those skilled in the art that the structure shown in FIG. 1 is merely illustrative and does not limit the structure of the above electronic device. For example, the mobile terminal 10 may also include more or fewer components than those shown in FIG. 1, or have a different configuration than that shown in FIG.

The memory 104 can be configured as a software program and a module for storing application software, such as program instructions/modules corresponding to the push method of the text resource in the embodiment of the present application, and the processor 102 runs the software program and the module stored in the memory 104. Thereby performing various functional applications and data processing, that is, implementing the above method. Memory 104 may include high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, memory 104 may further include memory remotely located relative to processor 102, which may be connected to mobile terminal 10 over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Transmission device 106 is arranged to receive or transmit data via a network. The network instance described above may include a wireless network provided by a communication provider of the mobile terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module configured to communicate with the Internet wirelessly.

In this embodiment, a method for pushing a text resource is provided. FIG. 2 is a flowchart of a method for pushing a text resource according to an embodiment of the present application. As shown in FIG. 2, the process includes the following steps:

Step S202, determining a target text type of the first text acquired by the client;

Step S204, searching for a plurality of second texts of the target text type in the preset text set;

Step S206, determining a first similarity between the first text and the plurality of second texts;

Step S208, determining that the second text whose first similarity meets the preset condition is the target text;

In step S210, the target text is pushed to the client.

Optionally, the pushing method of the text resource may be, but is not limited to, being applied to a scenario in which a text resource is pushed for a user. For example, a scene in which a text resource is pushed for a user in a news information application, a scene in which a text resource is pushed for a user in a text resource reading application, and the like.

Optionally, the method for pushing the text resource may be, but is not limited to, being applied to a terminal device or a server device, etc., for example, the terminal device may include, but is not limited to, a mobile phone, a tablet computer, a PC computer, a smart wearable device, an intelligent electronic device, Smart home equipment and more.

Optionally, in the foregoing embodiment, the foregoing client may be, but is not limited to, a client that is an application, for example, the foregoing application may include, but is not limited to, a news information application, a text resource reading application, an instant messaging application, and a browser. Application and more.

Optionally, in the foregoing embodiment, the text type of the text resource may be, but is not limited to, divided according to the domain involved in the text resource, such as: sports, entertainment, technology, finance, military, and the like. The text type of the text resource can also be divided according to the classification rules in a certain type of text resource. For example, the judgment documents in the legal document are classified into the first-instance document, the second-instance document, etc. according to the trial level, and are classified according to the type of the case. It is a civil case file or an administrative case file; or the court transcript/judgment document in the legal document is divided into a trademark infringement dispute file, a life right dispute file, a divorce dispute file, and so on.

Optionally, in this embodiment, the preset condition may be set as a condition for acquiring the second text with the first higher similarity. For example, the first similarity is the highest, the first similarity is higher than a certain preset value, and the like.

In an optional implementation manner, the predicate document is an important written material and basis for a court referee case, and the court file is used as a case for the judge to intelligently recommend a similar case for the judge according to the current pre-document material. The important components include: trial transcripts, complaints, pleadings, etc. The referee document records the process and results of the court's trial of the case and is the carrier of the outcome of the litigation activity.

The pre-document includes the following information: the generalization of the nature of the legal relationship involved in the litigation case (the case); the appeal of the plaintiff or the appellant; the defense of the defendant or the appellee; the display, debate and cross-examination of the evidence of the parties Comments and so on. This information is an important reference for judges to make litigation decisions. The referee documents also include the above information, in addition to the court's arguments on the case, the applicable law of the judge's decision and the outcome of the referee.

The server receives the first text obtained by the client, and the first text is a pre-document of the current pending case, and the text type of the pre-document can be classified into a trademark infringement dispute, a right to life dispute, a divorce dispute, etc. according to the case type. Divided into civil cases, administrative cases, criminal cases, the server determines that the target text type of the current pre-document is a civil case of trademark infringement disputes, and the preset text collection includes a large number of judgment documents of the judged cases, in the preset text The search case in the collection is determined by the judgment document of the civil case for the trademark infringement dispute as the plurality of second texts, and the first similarity between the current pre-document and the judgment document of the civil case in which the case is a trademark infringement dispute is determined. A similarity is sorted, and the top 10 judges are determined as the target text, and the target text is pushed to the client.

Through the above steps, searching for a plurality of second texts of the same text type from the preset text set according to the obtained target text type of the first text, thereby ensuring that the pushed text resource is of the same type as the text that the user desires to find. a text resource, and then obtaining a second text having a higher degree of similarity to the first text as the target text from the plurality of second texts found, and pushing the target text to the client, so that the text resource of the pushed client is The first text obtained by the client has the same text type and is similar, which improves the pertinence and validity of pushing the text resource to the client, thereby improving the pushing efficiency of the text resource, thereby solving the text resource in the related art. Pushing low efficiency issues.

Optionally, in determining the first similarity, the first text may be divided into a plurality of first text blocks, and respectively determined between the first text block and the second text block in the second text. A target similarity is further weighted according to the degree of influence of each text block on the similarity between the two texts, thereby determining a first similarity between the first text and each second text. For example, in the above step S206, the first text is divided according to the plurality of first keywords to obtain a first text block set, wherein the first keyword is used to indicate a feature of the text paragraph, the first keyword and the first The first text blocks in the set of text blocks are in one-to-one correspondence, and the first keyword is in one-to-one correspondence with the second text blocks in each second text, and the first text block corresponding to each first keyword is determined The first target similarity between the two text blocks, and determining the first similarity according to the first preset weight corresponding to each first target similarity and the first target similarity.

Optionally, in this embodiment, the second text block in the second text may be, but is not limited to, being pre-processed and parsed by the server, and the second text block may be multiple, and the server may follow the paragraph content. The feature parses the second text into a plurality of second text blocks. For example, the server can parse the judgment documents in the judgment document library, and analyze the following paragraphs: the appeal section, the defense section, the evidence section, the cross-examination opinion section, the dispute focus section, the trial identification section, the court thinks that the paragraph, etc. .

In the above optional implementation manner, the server performs paragraph analysis on the trial transcript in the first text, and obtains the following description segment: the original telling paragraph (the facts and reasons of the prosecution filed by the plaintiff and the lawsuit request); the defendant reply segment (the defendant For the original statement, please provide a statement of opinion; the evidence paragraph (the two parties show the evidence); the cross-examination opinion and the debate paragraph (the mutual cross-examination and debate between the parties); the court inquiry section (the court's inquiry and the parties' answers)

The server analyzes the paragraph of the complaint or the appeal, and obtains the following description: the original telling paragraph and the fact reason description. A paragraph analysis of the defense or appeal reply is obtained as follows: Defendant's defense.

The above first text block includes: the complaint (appeal section) + appeal (the appeal section), the reply (the defense section) + the appeal reply (the defense section), the trial transcript (the court investigation and debate section) + Complaint (de facto reason section).

3 is a schematic diagram of determining a first similarity according to an optional embodiment of the present application. As shown in FIG. 3, the second text block of the second text includes: a referee document (a petition), a referee document (a reply segment) ), the judgment document (the factual recognition section + the court thinks the paragraph), the full text of the judgment document. The server determines the similarity of the first target of the complaint (appeal section) + appeal (the appeal section) and the judgment document (the appeal section) is S1, the reply (the defense paragraph) + the appeal reply (the defense paragraph) ) The similarity with the first target of the judgment document (the defense paragraph) is S2, the trial transcript (the court investigation and debate section) + the complaint (the factual reason section) and the judgment document (the fact finding section + the court thinks the paragraph) A target similarity is S3. The first preset weights corresponding to the first target similarity are W1, W2, and W3, respectively. The server determines the first similarity according to the first preset weight corresponding to the first target similarity and the first target similarity.

Optionally, the first similarity may be determined by one of the following methods:

In a first manner, the first weighted sum of the first target similarity is determined according to the first preset weight, and the first weighted sum is used as the first similarity.

For example, in the above optional embodiment, the first similarity P=W1*S1+W2*S2+W3*S3.

In the second manner, the first weighted average of the first target similarity is determined according to the first preset weight, and the first weighted average is used as the first similarity.

For example, in the above optional embodiment, the first similarity P=(W1*S1+W2*S2+W3*S3)/3.

The third method determines a second target similarity between the first text and the second text, and determines that the first target similarity and the second target are similar according to the first preset weight and the second preset weight corresponding to the second target similarity The second weighted sum of degrees, the second weighted sum is taken as the first similarity.

For example, in the above optional implementation manner, the second target similarity between the first text and the second text is X, and the second predetermined weight corresponding to the second target similarity is V, and the first similarity is P=W1*S1+W2*S2+W3*S3+V*X.

And determining a second target similarity between the first text and the second text, and determining, according to the first preset weight and the second preset weight corresponding to the second target similarity, that the first target similarity and the second target are similar The second weighted average of degrees, the second weighted average is taken as the first similarity.

For example, in the above optional implementation manner, the second target similarity between the first text and the second text is X, and the second predetermined weight corresponding to the second target similarity is V, and the first similarity is P = (W1 * S1 + W2 * S2 + W3 * S3 + V * X) / 4.

Optionally, in this embodiment, determining a second target similarity between the first text and the second text, and considering the influence of the second target similarity on the first similarity between the two texts In the process of determining the similarity, it is possible to avoid screening out texts with a high degree of similarity but not similar in general.

Optionally, the target text may be determined from the plurality of second texts by one of the following methods:

In the first manner, the second text whose first similarity falls within the preset threshold range is determined as the target text. For example, if the preset threshold range is set to be higher than P0, the second text whose first similarity is greater than P0 is used as the target text.

In the mode 2, the second text is sorted according to the first similarity from high to low; and the second predetermined text in the preset number is determined as the target text. For example, if the preset number can be 1, the first text with the highest similarity among the plurality of second texts is determined as the target text. The preset number may be 10, and the first tenth similarity text is selected as the target text from the plurality of second texts.

Optionally, in the foregoing step S202, the target text type may be determined by: searching for the paragraph in which the second keyword is located in the first text, and determining the found paragraph as the feature paragraph, in the feature paragraph The third keyword is obtained, and the target text type corresponding to the third keyword is searched from the correspondence between the keyword and the text type.

Optionally, in this embodiment, the second keyword may be used to indicate a feature of the target text segment, the second keyword corresponds to a first text block in the first text block set, and the third keyword may be appealed. A keyword used to characterize a text type. For example, the first text mentioned above is a trial transcript, and the server searches for a paragraph in the trial transcript that the second keyword "announces the hearing" and identifies the paragraph as a feature paragraph, in which the third keyword "trademark rights" is obtained. In the dispute, the server can search for the target text type corresponding to the “trademark dispute” from the correspondence between the keyword and the text type as the trademark ownership dispute case.

In the above optional embodiment, the case, the level of the case and the type of the case in the pre-document can be analyzed, and the description of the case in the transcript of the trial is first extracted (in the paragraph section of the announcement). For example: "Trial: Announced the opening of the court. The Beijing xxx People's Court, today applies the ordinary procedure in accordance with the law to publicly hear the plaintiff xxx v. the defendant xx trademark ownership dispute case, the case is judged by the court's acting judge xxx as the presiding judge, and the court The acting judges xxx, xxx form a collegiate panel according to law, and the clerk xxx serves as the court record." The server extracts the case (trademark ownership dispute) and resolves the type of case (civil or administrative).

In the embodiment, a text resource pushing device is further provided, which is used to implement the above-mentioned embodiments and optional embodiments, and has not been described again. As used below, the term "module" may implement a combination of software and/or hardware of a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.

FIG. 4 is a structural block diagram 1 of a text resource pushing apparatus according to an embodiment of the present application. As shown in FIG. 4, the apparatus includes:

The first determining module 402 is configured to determine a target text type of the first text acquired by the client;

The searching module 404 is coupled to the first determining module 402, and configured to search, in the preset text set, a plurality of second texts of a type of the target text type;

a second determining module 406, coupled to the lookup module 404, configured to determine a first similarity between the first text and the plurality of second texts;

The third determining module 408 is coupled to the second determining module 406, and is configured to determine that the second text whose first similarity meets the preset condition is the target text;

The push module 410, coupled to the third determination module 408, is configured to push the target text to the client.

Optionally, the pushing device of the text resource may be, but is not limited to, applied to a scenario in which a text resource is pushed for a user. For example, a scene in which a text resource is pushed for a user in a news information application, a scene in which a text resource is pushed for a user in a text resource reading application, and the like.

Optionally, the pushing device of the text resource may be, but is not limited to, being applied to a terminal device or a server device, etc., for example, the terminal device may include, but is not limited to, a mobile phone, a tablet computer, a PC computer, a smart wearable device, an intelligent electronic device, Smart home equipment and more.

Optionally, in the foregoing embodiment, the client may be, but is not limited to, a client that is an application, for example, the application may be, but not limited to, an envelope: a news information application, a text resource reading application, an instant messaging application, and browsing. Applications and more.

Through the above device, searching for a plurality of second texts of the same text type from the preset text set according to the acquired target text type of the first text, thereby ensuring that the pushed text resource is of the same type as the text that the user desires to find. a text resource, and then obtaining a second text having a higher degree of similarity to the first text as the target text from the plurality of second texts found, and pushing the target text to the client, so that the text resource of the pushed client is The first text obtained by the client has the same text type and is similar, which improves the pertinence and validity of pushing the text resource to the client, thereby improving the pushing efficiency of the text resource, thereby solving the text resource in the related art. Pushing low efficiency issues.

FIG. 5 is a block diagram of a structure of a text resource pushing apparatus according to an embodiment of the present application. As shown in FIG. 5, optionally, the second determining module 406 includes:

The dividing unit 52 is configured to divide the first text according to the plurality of first keywords to obtain a first text block set, wherein the first keyword is used to indicate a feature of the text paragraph, the first keyword and the first text The first text blocks in the block set are in one-to-one correspondence, and the first keyword is in one-to-one correspondence with the second text block in each second text;

The first determining unit 54, coupled to the dividing unit 52, is configured to determine a first target similarity between the first text block and the second text block corresponding to each first keyword;

The second determining unit 56 is coupled to the first determining unit 54 and configured to determine the first similarity according to the first target weight corresponding to each first target similarity and the first target similarity.

Optionally, in determining the first similarity, the first text may be divided into a plurality of first text blocks, and respectively determined between the first text block and the second text block in the second text. A target similarity is further weighted according to the degree of influence of each text block on the similarity between the two texts, thereby determining a first similarity between the first text and each second text.

Alternatively, the second determining unit 56 is set to one of the following:

Determining, according to the first preset weight, a first weighted sum of the first target similarity, and using the first weighted sum as the first similarity; for example, in the foregoing optional implementation manner, the first similarity P=W1*S1+ W2*S2+W3*S3.

Determining, by the first preset weight, a first weighted average of the first target similarity, and using the first weighted average as the first similarity; for example, in the foregoing optional embodiment, the first similarity P=(W1 *S1+W2*S2+W3*S3)/3.

Determining a second target similarity between the first text and the second text; determining a first target similarity and a second target similarity according to the first preset weight and the second preset weight corresponding to the second target similarity a second weighted sum, the second weighted sum is taken as the first similarity; for example, in the above optional embodiment, the second target similarity between the first text and the second text is X, the second target similarity The corresponding second preset weight is V, and the first similarity P=W1*S1+W2*S2+W3*S3+V*X.

Determining a second target similarity between the first text and the second text; determining a first target similarity and a second target similarity according to the first preset weight and the second preset weight corresponding to the second target similarity The two weighted averages take the second weighted average as the first similarity. For example, in the above optional implementation manner, the second target similarity between the first text and the second text is X, and the second predetermined weight corresponding to the second target similarity is V, and the first similarity is P = (W1 * S1 + W2 * S2 + W3 * S3 + V * X) / 4.

Optionally, the third determining module 408 is set to one of the following:

Determining that the second text whose first similarity falls within the preset threshold range is the target text; for example, if the preset threshold range is set to be higher than P0, the second text whose first similarity is greater than P0 is used as the target text.

Sorting the second text from high to low according to the first similarity; determining that the second predetermined text is the target text. For example, if the preset number can be 1, the first text with the highest similarity among the plurality of second texts is determined as the target text. The preset number may be 10, and the first tenth similarity text is selected as the target text from the plurality of second texts.

FIG. 6 is a block diagram 3 of a structure of a text resource pushing apparatus according to an embodiment of the present application. As shown in FIG. 6 , optionally, the first determining module 402 includes:

The first searching unit 62 is configured to search for a paragraph in which the second keyword is located in the first text, and determine the found paragraph as a feature paragraph;

An obtaining unit 64, coupled to the first searching unit 62, configured to acquire a third keyword in the feature paragraph;

The second searching unit 66 is coupled to the obtaining unit 64 and configured to search for the target text type corresponding to the third keyword from the correspondence between the keyword and the text type.

Optionally, in this embodiment, the second keyword may be used to indicate a feature of the target text segment, the second keyword corresponds to a first text block in the first text block set, and the third keyword may be appealed. A keyword used to characterize a text type.

For example, the first text mentioned above is a trial transcript, and the server searches for a paragraph in the trial transcript that the second keyword "announces the hearing" and identifies the paragraph as a feature paragraph, in which the third keyword "trademark rights" is obtained. In the dispute, the server can search for the target text type corresponding to the “trademark dispute” from the correspondence between the keyword and the text type as the trademark ownership dispute case.

It should be noted that each of the above modules may be implemented by software or hardware. For the latter, the foregoing may be implemented by, but not limited to, the foregoing modules are all located in the same processor; or, the modules are located in multiple In the processor.

The above embodiments are only used to describe the technical solutions of the present application, and the technical solutions of the present application may be modified or equivalently replaced by those skilled in the art without departing from the spirit and scope of the present application. The scope of protection shall be as stated in the claims.

The embodiment of the present application further provides a storage medium including a stored program, wherein the program runs to perform the method described in any of the above.

Optionally, in the embodiment, the foregoing storage medium may be configured to store program code for performing the following steps:

S1, determining a target text type of the first text acquired by the client;

S2, searching for a plurality of second texts of the target text type in the preset text collection;

S3. Determine a first similarity between the first text and the plurality of second texts.

S4, determining that the second text whose first similarity meets the preset condition is the target text;

S5, the target text is pushed to the client.

Optionally, in the embodiment, the foregoing storage medium may include, but is not limited to, a USB flash drive, a Read-Only Memory (ROM), and a Random Access Memory (RAM). A variety of media that can store program code, such as a hard disk, a disk, or an optical disk.

Embodiments of the present application also provide a processor for running a program, wherein the program is executed to perform the steps of any of the above methods.

Optionally, in this embodiment, the foregoing program is used to perform the following steps:

S1, determining a target text type of the first text acquired by the client;

S5, the target text is pushed to the client.

For an alternative example in this embodiment, reference may be made to the examples described in the foregoing embodiments and the optional embodiments, and details are not described herein again.

Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, which can be concentrated on a single computing device or distributed in a network composed of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein. The steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module. Thus, the application is not limited to any particular combination of hardware and software.

The above description is only an optional embodiment of the present application, and is not intended to limit the present application, and various changes and modifications may be made to the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of this application are intended to be included within the scope of the present application.

Industrial applicability:

According to the above description, the application searches for a plurality of second texts of the same text type from the preset text set according to the obtained target text type of the first text, so as to ensure that the pushed text resource is desired by the user. a text resource of the same type as the text, and then obtaining a second text having a higher similarity with the first text as the target text from the plurality of second texts found, and pushing the target text to the client, so that the text of the pushed client is The resource has the same text type and similarity as the first text obtained from the client, which improves the pertinence and effectiveness of pushing the text resource to the client, thereby improving the pushing efficiency of the text resource, thereby solving the related technology Chinese The problem of low efficiency of pushing this resource.

Claims

A method for pushing text resources, including:

Determining the target text type of the first text obtained by the client;

Finding a plurality of second texts of the type of the target text in a preset text collection;

Determining a first similarity between the first text and the plurality of second texts;

Determining that the second text whose first similarity satisfies the preset condition is the target text;

Pushing the target text to the client.
The method of claim 1, wherein determining the first similarity between the first text and the plurality of second texts comprises:

And dividing the first text according to the plurality of first keywords to obtain a first text block set, wherein the first keyword is used to indicate a feature of a text segment, the first keyword and the first keyword The first text blocks in the set of text blocks are in one-to-one correspondence, and the first keywords are in one-to-one correspondence with the second text blocks in each of the second texts;

Determining a first target similarity between the first text block and the second text block corresponding to each of the first keywords;

The first similarity is determined according to the first preset weight corresponding to each of the first target similarities and the first target similarity.
The method according to claim 2, wherein determining the first similarity according to the first preset weight corresponding to each of the first target similarities and the first target similarity comprises one of the following:

Determining, according to the first preset weight, a first weighted sum of the first target similarity, using the first weighted sum as the first similarity;

Determining, according to the first preset weight, a first weighted average of the first target similarity, and using the first weighted average as the first similarity;

Determining a second target similarity between the first text and the second text; determining the first target according to the first preset weight and the second preset weight corresponding to the second target similarity a second weighted sum of the similarity and the second target similarity, the second weighted sum being the first similarity;

Determining a second target similarity between the first text and the second text; determining the first target according to the first preset weight and the second preset weight corresponding to the second target similarity a second weighted average of the similarity and the second target similarity, and the second weighted average is used as the first similarity.
The method according to claim 1, wherein the determining that the second text whose first similarity satisfies the preset condition is the target text comprises one of the following:

Determining that the second text whose first similarity falls within a preset threshold range is the target text;

Sorting the second text according to the first similarity from high to low; determining that the second predetermined number of the second texts are the target text.
The method according to any one of claims 1 to 4, wherein determining the target text type of the first text acquired by the client comprises:

Finding a paragraph in which the second keyword is located in the first text, and determining the found paragraph as a feature paragraph;

Obtaining a third keyword in the feature paragraph;

Searching for the target text type corresponding to the third keyword from a correspondence between a keyword and a text type.
A push device for text resources, comprising:

a first determining module, configured to determine a target text type of the first text acquired by the client;

a lookup module configured to look up a plurality of second texts of the target text type in a preset text collection;

a second determining module, configured to determine a first similarity between the first text and the plurality of second texts;

a third determining module, configured to determine that the second text whose first similarity meets the preset condition is the target text;

A push module is arranged to push the target text to the client.
The apparatus of claim 6, wherein the second determining module comprises:

a dividing unit, configured to divide the first text according to the plurality of first keywords to obtain a first text block set, wherein the first keyword is used to indicate a feature of a text segment, the first key The words are in one-to-one correspondence with the first text block in the first set of text blocks, and the first keyword is in one-to-one correspondence with the second text block in each of the second texts;

a first determining unit, configured to determine a first target similarity between the first text block and the second text block corresponding to each of the first keywords;

The second determining unit is configured to determine the first similarity according to the first preset weight corresponding to each of the first target similarities and the first target similarity.
The apparatus according to claim 6 or 7, wherein the first determining module comprises:

a first searching unit, configured to search for a paragraph in which the second keyword is located in the first text, and determine the found paragraph as a feature paragraph;

An obtaining unit, configured to obtain a third keyword in the feature paragraph;

The second searching unit is configured to search for the target text type corresponding to the third keyword from a correspondence between the keyword and the text type.
A storage medium, the storage medium comprising a stored program, wherein the program is executed to perform the method of any one of claims 1 to 5.
A processor for running a program, wherein the program is executed to perform the method of any one of claims 1 to 5.