CN114281981B - News brief report generation method and device and electronic equipment - Google Patents
News brief report generation method and device and electronic equipment Download PDFInfo
- Publication number
- CN114281981B CN114281981B CN202111581490.5A CN202111581490A CN114281981B CN 114281981 B CN114281981 B CN 114281981B CN 202111581490 A CN202111581490 A CN 202111581490A CN 114281981 B CN114281981 B CN 114281981B
- Authority
- CN
- China
- Prior art keywords
- news
- target
- initial
- abstract
- event
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The disclosure provides a method and a device for generating news briefs and electronic equipment, and relates to the technical field of artificial intelligence such as knowledge maps. The specific implementation scheme is as follows: when automatically generating the news bulletin, at least one news event corresponding to the target person in a preset time period can be acquired first; determining a target news material corresponding to the news event; generating a target abstract corresponding to the target news material; wherein the target abstract includes viewpoint information of news events; and generating news briefs according to the target abstract comprising the viewpoint information. Compared with the direct generation of the news briefs based on the target news materials, the news briefs are simplified in content, and the news briefs explicitly comprise the viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news briefs.
Description
Technical Field
The disclosure relates to the technical field of data processing, in particular to the technical field of artificial intelligence such as knowledge maps, and specifically relates to a method and a device for generating news bulletins and electronic equipment.
Background
With the explosive growth of news materials, a news material library includes a large number of news materials corresponding to news events. By means of news bulletins, news materials corresponding to related news events can be displayed to users rapidly.
Therefore, how to automatically generate news bulletins is a problem to be solved by those skilled in the art.
Disclosure of Invention
The method, the device and the electronic equipment for generating the news briefs can automatically generate the news briefs, and the news briefs explicitly comprise viewpoint information corresponding to the news events, so that a user can quickly acquire the viewpoint information of the news events through the news briefs.
According to a first aspect of the present disclosure, a method for generating a news bulletin is provided, where the method for generating a news bulletin may include:
and acquiring at least one news event corresponding to the target person in a preset time period.
Determining target news materials corresponding to the news events, and generating target abstracts corresponding to the target news materials; and the target abstract comprises viewpoint information of the news event.
And generating a news bulletin according to the target abstract.
According to a second aspect of the present disclosure, there is provided a news bulletin generating apparatus, which may include:
The acquisition unit is used for acquiring at least one news event corresponding to the target person in a preset time period;
the processing unit is used for determining target news materials corresponding to the news events and generating target abstracts corresponding to the target news materials; wherein, the target abstract comprises viewpoint information of the news event;
and the generating unit is used for generating a news bulletin according to the target abstract.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of generating a news bulletin as described in the first aspect above.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method for generating a news bulletin according to the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the method of generating a news bulletin as described in the first aspect above.
According to the technical scheme, the news bulletin can be automatically generated, and the news bulletin clearly comprises the viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news bulletin.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a flowchart illustrating a method for generating a news bulletin according to a first embodiment of the present disclosure;
FIG. 2 is a flowchart of a method for determining target news materials and generating a target abstract corresponding to the target news materials according to a second embodiment of the disclosure;
fig. 3 is a flowchart illustrating a method for generating a news bulletin according to a target abstract according to a third embodiment of the present disclosure;
FIG. 4 is a schematic illustration of a news bulletin provided by an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a news bulletin generating apparatus provided according to a third embodiment of the present disclosure;
Fig. 6 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In embodiments of the present disclosure, "at least one" means one or more, and "a plurality" means two or more. "and/or" describes the access relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may represent: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In the text description of the present disclosure, the character "/" generally indicates that the front-rear associated object is an or relationship. Furthermore, in the embodiments of the present disclosure, "first", "second", "third", "fourth", "fifth" and "sixth" are only for distinguishing contents of different objects, and have no other special meaning.
The technical scheme provided by the embodiment of the disclosure can be applied to the technical field of artificial intelligence such as knowledge graph and the like. Taking a news bulletin generation scene in the field of knowledge maps as an example, along with the explosive growth of news materials, a news material library comprises a large number of news materials corresponding to news events. By means of news bulletins, news materials corresponding to related news events can be displayed to users rapidly.
In the prior art, when a news bulletin is automatically generated, after a news material corresponding to a news event is acquired, the news bulletin is directly generated based on the news event and the news material corresponding to the news event without processing the news material corresponding to the news event. However, such news briefs are typically news for the general field of news, such as entertainment news, or traffic accident news, and the news briefs in these fields only need to describe news events. However, for news in a specific field of news, for example, news that explicitly indicates viewpoint information, etc., news bulletins in these fields need to describe not only news events but also viewpoint information corresponding to the news events, and therefore, how to automatically generate news bulletins, and it is important that the viewpoint information corresponding to the news events be included in the bulletins.
In order to automatically generate a news bulletin, wherein the news bulletin clearly comprises viewpoint information corresponding to news events, after at least one news event corresponding to a target person in a preset time period is acquired, news materials corresponding to the news event can be determined first and can be recorded as target news materials; generating a target abstract which corresponds to the target news material and comprises viewpoint information; and generating news briefs according to the target abstract comprising the viewpoint information. Compared with the direct generation of the news briefs based on the target news materials, the news briefs are simplified in content, and the news briefs explicitly comprise the viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news briefs.
Based on the technical conception described above, the embodiment of the present disclosure provides a method for generating a news bulletin, and the method for generating a news bulletin provided by the present disclosure will be described in detail by a specific embodiment. It is to be understood that the following embodiments may be combined with each other and that some embodiments may not be repeated for the same or similar concepts or processes.
Example 1
Fig. 1 is a flowchart of a method for generating a news bulletin, which may be performed by software and/or hardware devices, for example, a terminal or a server, according to a first embodiment of the present disclosure. For example, referring to fig. 1, the method for generating a news bulletin may include:
s101, acquiring at least one news event corresponding to a target person in a preset time period.
For example, the preset time period may be three days, may be one week, may be one month, or the like, and may specifically be set according to actual needs, where the value of the preset time period is not specifically limited in the embodiments of the present disclosure.
For example, the target person may be a certain person, a certain group, or the like, and may be specifically set according to actual needs.
For example, when a news briefing generation request is detected, if the news briefing to be generated is a news briefing corresponding to the target person in the preset time period, the generation request generally includes the preset time period and the identifier of the target person; correspondingly, at least one news event corresponding to the target person in the preset time period is acquired according to the generation request.
For example, when at least one news event corresponding to the target person in the preset time period is acquired, at least one news event corresponding to the target person in the preset time period sent by other electronic equipment may be received; at least one news event corresponding to the target person in the preset time period can also be obtained from the local storage; at least one news event corresponding to the target person in the preset time period can be acquired by other methods; the setting can be specifically performed according to actual needs.
After acquiring at least one news event corresponding to the target person within the preset time period, the following S102 may be executed:
s102, determining target news materials corresponding to news events, and generating target abstracts corresponding to the target news materials; wherein, the target abstract comprises viewpoint information of news event.
For example, a news event may correspond to a target news material; multiple target news materials can also be corresponding; in the embodiment of the disclosure, taking a news event corresponding to a target news material as an example, the content redundancy of the news event caused by a plurality of target news materials can be avoided, and the content redundancy of the news event in the generated news bulletin can be further avoided when the news bulletin is generated based on the target news materials.
After determining the target news material corresponding to the news event, a target abstract corresponding to the target news material can be generated based on the target news material. For example, a target news material corresponds to a target abstract; multiple target summaries may also be corresponded; in the embodiment of the disclosure, taking an example that one target news material corresponds to one target abstract, content redundancy of news events in the generated news bulletin caused by a plurality of target abstracts can be avoided.
After generating the target abstract including the viewpoint information corresponding to the news event, the news bulletin may be generated according to the target abstract, that is, the following S103 is executed:
s103, generating a news bulletin according to the target abstract.
The news bulletin comprises a target abstract of a news event corresponding to a target person in a preset time period, and the target abstract comprises viewpoint information corresponding to the news event.
It can be seen that, in the embodiment of the present disclosure, when a news bulletin is automatically generated, at least one news event corresponding to a target person in a preset time period may be acquired first; determining a target news material corresponding to the news event; generating a target abstract corresponding to the target news material; wherein the target abstract includes viewpoint information of news events; and generating news briefs according to the target abstract comprising the viewpoint information. Compared with the direct generation of the news briefs based on the target news materials, the news briefs are simplified in content, and the news briefs explicitly comprise the viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news briefs.
Based on the embodiment shown in fig. 1, in order to facilitate understanding how to determine the target news material corresponding to the news event and generate the target abstract corresponding to the target news material in S102, a detailed description will be given below with respect to the second embodiment shown in fig. 2.
Example two
Fig. 2 is a flowchart of a method for determining target news materials and generating a target abstract corresponding to the target news materials according to a second embodiment of the disclosure, which may be performed by software and/or hardware devices. For example, referring to fig. 2, the method may include:
s201, acquiring a plurality of initial news materials corresponding to news events; wherein, there is a degree of association between the initial news material and the news event.
The association degree between the initial news material and the news event may be determined based on the source of the initial news material, and/or the occurrence time of the news event recorded in the initial news material, and/or whether the entity extracted from the text of the initial news material accords with the news event, and may be specifically set according to actual needs.
In general, after a news event occurs, a plurality of corresponding news materials appear, and the news events and the corresponding news materials can be stored in a news material library in a mapping relationship manner, that is, the news material library comprises mapping relationships between each news event and the corresponding news material; in addition, the association degree between each news material and the corresponding news event can be marked together. For example, in order to ensure the quality of news materials in a news material library, when the news materials are stored in the news material library, the news materials can be screened by evaluating the quality of the news materials. In the screening, news materials with lower quality, such as too short a space of the news materials, and/or obvious errors of occurrence time of news events recorded in the news materials, need not be stored in a news material library.
For example, in the embodiment of the present disclosure, when acquiring a plurality of initial news materials corresponding to a news event, the plurality of news materials corresponding to the news event may be searched from a news material library according to a mapping relationship between the news event and the news material, and in order to facilitate differentiation, in the embodiment of the present disclosure, the plurality of news materials may be recorded as a plurality of initial news materials, so as to acquire a plurality of initial news materials corresponding to the news event.
After a plurality of initial news materials corresponding to the news event are acquired, considering that the plurality of initial news materials are all used for describing the same news event, if the plurality of initial news materials are simultaneously used as target news materials corresponding to the news event, the content redundancy of the news event can be caused, so that the content redundancy of the news event in the news briefing generated based on the target news material is caused, and therefore, in order to avoid the content redundancy, one news material can be determined from the plurality of initial news materials and used as the target news material corresponding to the news event, so that the target news material is used for automatically generating the news briefing subsequently. For example, in determining the target news material from the plurality of initial news materials, the target news material may be determined from the plurality of initial news materials according to the association degree corresponding to each initial news material in the plurality of initial news materials, that is, the following S202 is executed:
S202, determining target news materials from a plurality of initial news materials according to the association degree corresponding to the initial news materials.
For example, when determining the target news material from the plurality of initial news materials according to the association degree corresponding to the initial news materials, whether the initial news materials meet the preset rule may be determined from the initial news material with the highest association degree according to the order of the association degree corresponding to each initial news material from high to low; and determining the initial news material meeting the preset rule as the target news material. For example, the preset rule may include that the text space of the news material meets the space requirement of the target news material, the extraction quality of the important information in the news material meets the quality requirement of the target news material, and the like, and may be specifically set according to the actual requirement, where the embodiment of the disclosure only uses the preset rule including these two factors as an example for illustration, but the embodiment of the disclosure is not limited thereto. By way of example, the important information may include information related to a person, an occurrence time, an occurrence place, and a viewpoint, etc.
When determining the target news material from the plurality of initial news materials according to the sequence from high to low of the association degree corresponding to each initial news material, determining the initial news material with the highest association degree with the news event from the plurality of initial news materials, and judging whether the initial news material with the highest association degree meets a preset rule; if yes, directly determining the initial news material with the highest association degree as a target news material; if the initial news material is not met, determining initial news materials with the next highest association degree with the news event from a plurality of initial news materials, and judging whether the initial news materials with the next highest association degree meet a preset rule; if yes, determining the initial news material with the next highest association degree as a target news material; if the initial news material is not met, determining an initial news material with the third highest association degree with the news event from a plurality of initial news materials, judging the initial news material which meets the preset rule, and determining the initial news material as a target news material.
After determining the target news material in the plurality of initial news materials, the abstract corresponding to the target news material may be further generated, for convenience of distinction, the abstract corresponding to the target news material may be generated as the initial abstract, that is, the following S203 is executed:
s203, generating an initial abstract corresponding to the target news material.
Typically, each news material will have a respective title and body. When generating the initial abstract corresponding to the target news material, for example, an abstract generation operator in a natural language processing technology may be invoked to process the target news material, thereby generating the initial abstract corresponding to the target news material.
It can be understood that by calling the abstract generation operator in the natural language processing technology, the initial abstract corresponding to the target news material is generated, which has the advantages that: the method can generate the initial abstract with the preset word number, wherein the number of the preset word number is smaller than that of the text of the target news material, so that the target news material can be simplified, the news briefs are generated based on the initial abstract, and compared with the news briefs generated directly based on the target news material, the news briefs are simplified in content.
After the initial abstract corresponding to the target news material is generated, the initial abstract is corresponding to the target news material in addition to the respective title and text.
For news in a specific field of news, for example, news that explicitly indicates viewpoint information, etc., news bulletins in these fields need to explicitly indicate not only news events but also viewpoint information corresponding to the news events, and therefore, when generating such news bulletins, it is also necessary to determine that viewpoint information is included in the abstract for describing news events.
Based on the above consideration, after the initial summary corresponding to the target news material is generated, it is further required to determine whether the generated initial summary includes keywords, that is, the following S204 is executed:
s204, judging whether the initial abstract comprises keywords or not, and representing viewpoint information by sentences in which the keywords are located.
By way of example, keywords may be "point out", "emphasize", etc., words used to express viewpoint information. Typically, the content immediately following the keyword is noted as viewpoint information of the news event.
For example, when judging whether the initial abstract includes keywords, the initial abstract may be sequentially traversed based on rule extraction to judge whether keywords for expressing viewpoint information exist; other algorithms can be adopted to traverse the initial abstract, judge whether keywords for expressing viewpoint information exist or not, and specifically set according to actual needs.
After the judgment, if it is determined that the initial abstract includes the keyword, the following S205 is executed; in contrast, if it is determined that the keywords are not included in the initial digest, the following S206 is performed.
S205, if the initial abstract includes keywords, determining a target abstract according to the initial abstract.
If the initial abstract includes keywords, and the initial abstract includes viewpoint information corresponding to the news event, the target abstract can be determined directly according to the initial abstract.
For example, when determining the target abstract according to the initial abstract, the occurrence time of the news event corresponding to the initial abstract can be determined first; and determining a target summary based on the time of occurrence, the target persona, the news event, and the initial summary.
For example, when determining the occurrence time of the news event corresponding to the initial abstract, an event extraction operator of the event map may be invoked to extract the occurrence time of the target news material corresponding to the initial abstract, and in addition, the target person in the target news material may be extracted together, and after determining the occurrence time, the target abstract may be determined according to the occurrence time, the target person, the news event, and the initial abstract.
By way of example, in determining the target digest based on the time of occurrence, the target character, the news event, and the initial digest, the content of the target digest may be described in at least three possible formats:
Format 1: x month and X day, XXX hosts XXXX and places speech emphasis on XXXXXXXXXXXXXX.
Format 2: x month X day, XXX hosts XXXX and speaks. XXX emphasizes XXXXXXXXXXXX.
Format 3: x month X day, XXX places speech emphasis on XXXX, XXXXXXXXXXXX.
It should be noted that, in the three possible formats described above, X month and X day represent the time of occurrence, XXX represents the target person, XXXX represents the news event, and xxxxxxxxxxx represents the initial summary.
It will be appreciated that in determining the target summary based on the time of occurrence, the target persona, the news event, and the initial summary, the three possible formats described above are merely illustrative and are not intended to be limiting as to the embodiments of the disclosure.
In this case, if the initial abstract includes a keyword, the target abstract may be determined directly according to the initial abstract, and the target abstract includes viewpoint information corresponding to the news event; therefore, compared with the fact that the news bulletin is directly generated based on the target news materials, the news bulletin is simplified in content, and the news bulletin clearly comprises viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news bulletin.
S206, if the initial abstract does not contain keywords, determining the news event as viewpoint information; and adding the target character, the keywords and the viewpoint information into the initial abstract, and determining the target abstract according to the updated abstract.
If the initial abstract does not include keywords, it is explained that the initial abstract does not include viewpoint information corresponding to news events, so that the viewpoint information is included in the target abstract for generating news bulletin, therefore, the news events can be determined as viewpoint information, and the target characters, keywords and viewpoint information can be added into the initial abstract, so that the updated abstract includes the viewpoint information.
For example, when the target person, the keyword and the viewpoint information are added to the initial abstract, the target person, the keyword and the viewpoint information may be added to the final part of the initial abstract in a manner of, for example, "target person+keyword+viewpoint information", so that an updated abstract may be obtained, and the updated abstract includes viewpoint information corresponding to the news event.
After the updated summary is obtained, a target summary may be determined from the updated summary. For example, when determining the target abstract according to the updated abstract, similar to the method for determining the target abstract according to the initial abstract in S205, the occurrence time of the news event corresponding to the updated abstract is determined first; and determining a target abstract based on the time of occurrence, the target personage, the news event, and the updated abstract.
For example, when determining the occurrence time of a news event corresponding to the updated abstract, an event extraction operator of the event map may be invoked to extract the occurrence time in a target news material corresponding to the updated abstract, and in addition, a target person in the target news material may be extracted together, and after determining the occurrence time, the target abstract may be determined according to the occurrence time, the target person, the news event, and the updated abstract.
For example, when determining the target digest according to the occurrence time, the target character, the news event, and the updated digest, the content of the target digest may also be described in at least three possible formats:
format 1: x month X day, XXX hosts XXXX and places speech emphasis on XXXXXXXXXXXXXXX.
Format 2: x month X day, XXX hosts XXXX and speaks. XXX emphasizes XXXXXXXXXXXXX.
Format 3: x month X day, XXX places speech emphasis on XXXX, XXXXXXXXXXX.
It should be noted that, in the above three possible formats, X month and X day represent the time of occurrence, XXX represents the target person, XXXX represents the news event, and xxxxxxxxxxxxx represents the updated abstract.
It will be appreciated that in determining the target summary based on the time of occurrence, the target persona, the news event, and the updated summary, the three possible formats described above are merely illustrative and are not intended to be limiting as to the embodiments of the present disclosure.
In this case, if the keyword is not included in the initial digest, the news event may be determined as the viewpoint information; adding the target character, the keywords and the viewpoint information into the initial abstract, determining the target abstract according to the updated abstract, wherein the target abstract comprises viewpoint information corresponding to the news event; therefore, compared with the fact that the news bulletin is directly generated based on the target news materials, the news bulletin is simplified in content, and the news bulletin clearly comprises viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news bulletin.
It can be seen that, in the embodiment of the present disclosure, when determining a target news material corresponding to a news event, a plurality of initial news materials corresponding to the news event may be acquired first; determining target news materials from a plurality of initial news materials according to the association degree corresponding to the initial news materials; thus, the content redundancy of news events caused by simultaneously taking a plurality of initial news materials as target news materials corresponding to the news events can be avoided. In addition, when generating a target abstract corresponding to the target news material, an initial abstract corresponding to the target news material can be generated; judging whether the initial abstract comprises keywords or not, wherein sentences in which the keywords are located represent viewpoint information; if the initial abstract includes keywords, determining a target abstract according to the initial abstract; if the initial abstract does not contain keywords, determining the news event as viewpoint information; adding the target character, the keywords and the viewpoint information into the initial abstract, and determining a target abstract according to the updated abstract; therefore, compared with the fact that the news bulletin is directly generated based on the target news materials, the news bulletin is simplified in content, and the news bulletin clearly comprises viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news bulletin.
Based on any of the above embodiments, after generating the target abstract corresponding to the news event, the step S103 of generating the news bulletin according to the target abstract may be performed. In order to facilitate understanding of how the news bulletins are generated from the target abstract in S103 described above, a detailed description will be made below by way of a third embodiment shown in fig. 3 described below.
Example III
Fig. 3 is a flowchart illustrating a method for generating a news bulletin according to a target abstract, which may be performed by software and/or hardware devices, according to a third embodiment of the present disclosure. For example, referring to fig. 3, the method may include:
s301, generating a secondary title according to a preset format according to the target person and preset content.
For example, the preset content may be "the latest important talk and important instruction wholesale spirit", or may be other beauty treatment, and may be specifically set according to actual needs, where the embodiments of the disclosure will be described by taking the preset content as "the latest important talk and important instruction wholesale spirit", but the embodiments of the disclosure are not limited thereto.
For example, when generating the secondary title according to the preset format based on the target person and the preset content, assuming that the target person is represented by "XXX", and the preset content is "latest important talk and important instruction wholesale spirit", the secondary title generated according to the preset format may be "XXX latest important talk and important instruction wholesale spirit".
S302, generating a news bulletin according to a preset primary title, a preset secondary title and news event information corresponding to a target abstract; wherein the news event information includes a title and a target digest of the news event.
For example, when the news bulletin is a bulletin within a week, the preset primary title may be: important instructions wholesale mental interpretation and analysis week report; when the news bulletin is a bulletin in within one month, the preset primary title may be: important instructions wholesale mental interpretation and analysis month report; the setting can be specifically performed according to actual needs.
The generated news bulletin may include news event information corresponding to a preset primary title, a secondary title and a target abstract according to the preset primary title, the secondary title and the news event information corresponding to the target abstract. Wherein the news event information includes a title and a target digest of the news event.
For example, assuming that 3 news events corresponding to the target person are determined in the preset time period, where the 3 news events are respectively a news event a, a news event B and a news event C, where the occurrence time of the news event a is earlier than the occurrence time of the news event B and the occurrence time of the news event C, and the occurrence time of the news event B is earlier than the occurrence time of the news event C, the correspondingly generated news briefs may be shown in fig. 4, and fig. 4 is a schematic diagram of a news briefing provided in the embodiment of the present disclosure, and, as can be seen in conjunction with fig. 4, the news briefing shown in fig. 4 sequentially includes a preset primary title, a secondary title, news event information of the news event a, news event information of the news event B and news event information of the news event C.
It can be seen that, in the embodiment of the present disclosure, when generating a news bulletin according to the target abstract, a secondary title may be generated according to a preset format according to the target person and the preset content; generating a news bulletin according to the preset primary title, the preset secondary title and news event information corresponding to the target abstract; therefore, compared with the fact that the news bulletin is directly generated based on the target news materials, the news bulletin is simplified in content, and the news bulletin clearly comprises viewpoint information corresponding to the news event, so that a user can quickly acquire the viewpoint information of the news event through the news bulletin.
After the news briefs are generated according to the target abstract, the generated news briefs can be displayed and released. When the news briefs are displayed, the generated news briefs can be edited, and in addition, corresponding news maps can be inserted into the generated news briefs; and after the editing is completed, the generated news bulletin can be released for the user to check.
Example III
Fig. 5 is a schematic structural diagram of a news bulletin generating device 50 provided according to a third embodiment of the present disclosure, and as an example, referring to fig. 5, the news bulletin generating device 50 may include:
An obtaining unit 501, configured to obtain at least one news event corresponding to a target person in a preset period of time.
The processing unit 502 is configured to determine a target news material corresponding to a news event, and generate a target abstract corresponding to the target news material; wherein, the target abstract comprises viewpoint information of news event.
And the generating unit 503 is configured to generate a news bulletin according to the target abstract.
Optionally, the processing unit 502 includes a first processing module and a second processing module.
The first processing module is used for acquiring a plurality of initial news materials corresponding to the news event; wherein, there is a degree of association between the initial news material and the news event.
And the second processing module is used for determining target news materials from the plurality of initial news materials according to the association degree corresponding to the initial news materials.
Optionally, the second processing module includes a first processing sub-module and a second processing sub-module.
And the first processing sub-module is used for judging whether the initial news materials meet a preset rule or not from the initial news materials with the highest association degree according to the sequence from high to low of the association degree corresponding to each initial news material.
And the second processing sub-module is used for determining the initial news material meeting the preset rule as the target news material.
Optionally, the processing unit 502 further includes a third processing module, a fourth processing module, and a fifth processing module.
And the third processing module is used for generating an initial abstract corresponding to the target news material.
And the fourth processing module is used for judging whether the initial abstract comprises keywords or not, and the sentences in which the keywords are located represent viewpoint information.
And the fifth processing module is used for determining a target abstract according to the initial abstract if the initial abstract comprises keywords.
Optionally, the fifth processing module includes a third processing sub-module and a fourth processing sub-module.
And the third processing sub-module is used for determining the occurrence time of the news event corresponding to the initial abstract.
And a fourth processing sub-module for determining a target abstract according to the occurrence time, the target person, the news event and the initial abstract.
Optionally, the processing unit 502 further includes a sixth processing module and a seventh processing module.
And the sixth processing module is used for determining the news event as the viewpoint information if the initial abstract does not comprise the keywords.
And a seventh processing module, configured to add the target person, the keyword and the viewpoint information to the initial abstract, and determine the target abstract according to the updated abstract.
Optionally, the generating unit 503 includes a first generating module and a second generating module.
The first generation module is used for generating a secondary title according to a preset format according to the target person and preset content.
The second generation module is used for generating a news bulletin according to the preset first-level title, second-level title and news event information corresponding to the target abstract; wherein the news event information includes a title and a target digest of the news event.
Optionally, in the news bulletin, each piece of news event information is sequentially arranged according to the sequence from front to back of the occurrence time of each piece of news event.
The device 50 for generating a news bulletin according to the embodiments of the present disclosure may execute the technical scheme of the method for generating a news bulletin shown in any embodiment, and the implementation principle and the beneficial effects of the method are similar to those of the method for generating a news bulletin, and may refer to the implementation principle and the beneficial effects of the method for generating a news bulletin, which will not be described herein.
In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any one of the embodiments described above.
Fig. 6 is a schematic block diagram of an electronic device 60 provided by an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the device 60 includes a computing unit 601 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 60 can also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Various components in the device 60 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 60 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the respective methods and processes described above, for example, a news bulletin generating method. For example, in some embodiments, the method of generating a news bulletin may be implemented as a computer software program, which is tangibly embodied on a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 60 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the news bulletin generating method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the method of generating a news bulletin in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, 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), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (16)
1. A method for generating news bulletins comprises the following steps:
acquiring at least one news event corresponding to a target person in a preset time period;
determining target news materials corresponding to the news events, and generating target abstracts corresponding to the target news materials; wherein, the target abstract comprises viewpoint information of the news event;
generating a secondary title according to the target person and preset contents and a preset format;
Generating a news briefing according to a preset primary title, the secondary title and news event information corresponding to the target abstract; wherein the news event information includes a title of a news event and the target abstract.
2. The method of claim 1, wherein the determining the target news material corresponding to the news event comprises:
acquiring a plurality of initial news materials corresponding to the news event; wherein, the initial news material and the news event have a degree of association;
and determining the target news material from the plurality of initial news materials according to the association degree corresponding to the initial news materials.
3. The method of claim 2, wherein the determining the target news material from the plurality of initial news materials according to the relevance corresponding to the initial news material comprises:
judging whether the initial news materials meet a preset rule or not from the initial news materials with the highest association degree according to the sequence from high to low of the association degree corresponding to the initial news materials;
and determining the initial news material meeting the preset rule as the target news material.
4. A method according to any one of claims 1-3, wherein the generating a target summary corresponding to the target news material comprises:
generating an initial abstract corresponding to the target news material;
judging whether the initial abstract comprises keywords or not, wherein sentences in which the keywords are located represent viewpoint information;
and if the initial abstract contains the keywords, determining the target abstract according to the initial abstract.
5. The method of claim 4, the determining the target digest from the initial digest comprising:
determining the occurrence time of the news event corresponding to the initial abstract;
and determining the target abstract according to the occurrence time, the target person, the news event and the initial abstract.
6. The method of claim 4, the method further comprising:
if the initial abstract does not contain the keywords, determining the news event as the viewpoint information;
and adding the target person, the keywords and the viewpoint information into the initial abstract, and determining the target abstract according to the updated abstract.
7. The method of any one of claims 1-3 and 5-6, wherein in the news bulletin, each news event information is sequentially arranged in order of occurrence time of each news event from front to back.
8. A news bulletin generating device, comprising:
the acquisition unit is used for acquiring at least one news event corresponding to the target person in a preset time period;
the processing unit is used for determining target news materials corresponding to the news events and generating target abstracts corresponding to the target news materials; wherein, the target abstract comprises viewpoint information of the news event;
the generating unit comprises a first generating module and a second generating module;
the first generation module is used for generating a secondary title according to the target person and preset contents and a preset format;
the second generation module is used for generating a news bulletin according to a preset primary title, the secondary title and news event information corresponding to the target abstract; wherein the news event information includes a title of a news event and the target abstract.
9. The apparatus of claim 8, wherein the processing unit comprises a first processing module and a second processing module;
the first processing module is used for acquiring a plurality of initial news materials corresponding to the news event; wherein, the initial news material and the news event have a degree of association;
And the second processing module is used for determining the target news material from the plurality of initial news materials according to the association degree corresponding to the initial news materials.
10. The apparatus of claim 9, wherein the second processing module comprises a first processing sub-module and a second processing sub-module;
the first processing sub-module is used for judging whether the initial news materials meet a preset rule or not from the initial news materials with the highest association degree according to the sequence from high to low of the association degree corresponding to each initial news material;
and the second processing sub-module is used for determining the initial news material meeting the preset rule as the target news material.
11. The apparatus of any of claims 8-10, wherein the processing unit further comprises a third processing module, a fourth processing module, and a fifth processing module;
the third processing module is used for generating an initial abstract corresponding to the target news material;
the fourth processing module is configured to determine whether the initial abstract includes a keyword, where a sentence where the keyword is located represents viewpoint information;
and the fifth processing module is used for determining the target abstract according to the initial abstract if the initial abstract contains the keywords.
12. The apparatus of claim 11, the fifth processing module comprising a third processing sub-module and a fourth processing sub-module;
the third processing sub-module is used for determining the occurrence time of the news event corresponding to the initial abstract;
the fourth processing sub-module determines the target summary based on the time of occurrence, the target persona, the news event, and the initial summary.
13. The apparatus of claim 11, the processing unit further comprising a sixth processing module and a seventh processing module;
the sixth processing module is configured to determine the news event as the viewpoint information if the initial summary does not include the keyword;
the seventh processing module is configured to add the target person, the keyword, and the viewpoint information to the initial abstract, and determine the target abstract according to the updated abstract.
14. The apparatus of any of claims 8-10, 12-13, wherein the news bulletins have news event information arranged in sequence from front to back in order of occurrence time of each news event.
15. An electronic device, comprising:
At least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of generating a news bulletin as claimed in any one of claims 1 to 7.
16. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of generating a news bulletin according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111581490.5A CN114281981B (en) | 2021-12-22 | 2021-12-22 | News brief report generation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111581490.5A CN114281981B (en) | 2021-12-22 | 2021-12-22 | News brief report generation method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114281981A CN114281981A (en) | 2022-04-05 |
| CN114281981B true CN114281981B (en) | 2023-05-02 |
Family
ID=80873849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111581490.5A Active CN114281981B (en) | 2021-12-22 | 2021-12-22 | News brief report generation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114281981B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10162870B2 (en) * | 2015-09-30 | 2018-12-25 | International Business Machines Corporation | Historical summary visualizer for news events |
| CN108062389A (en) * | 2017-12-15 | 2018-05-22 | 北京百度网讯科技有限公司 | Bulletin generation method and device |
| CN108628833B (en) * | 2018-05-11 | 2021-01-22 | 北京三快在线科技有限公司 | Method and device for determining summary of original content and method and device for recommending original content |
| CN110263319A (en) * | 2019-03-21 | 2019-09-20 | 国家计算机网络与信息安全管理中心 | A kind of scholar's viewpoint abstracting method based on web page text |
| CN110489543B (en) * | 2019-08-14 | 2020-09-15 | 北京金堤科技有限公司 | News abstract extraction method and device |
| CN110597981B (en) * | 2019-09-16 | 2021-07-20 | 西华大学 | Network news summary system for automatically generating summary by adopting multiple strategies |
| CN113268598A (en) * | 2021-05-26 | 2021-08-17 | 平安科技（深圳）有限公司 | Event context generation method and device, terminal equipment and storage medium |
| CN113660541B (en) * | 2021-07-16 | 2023-10-13 | 北京百度网讯科技有限公司 | Method and device for generating abstract of news video |
| CN113641817A (en) * | 2021-08-30 | 2021-11-12 | 山东新一代信息产业技术研究院有限公司 | Report generation method and device based on subject and timeline abstract |
-
2021
- 2021-12-22 CN CN202111581490.5A patent/CN114281981B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114281981A (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11019012B2 (en) | File sending in instant messaging application | |
| CN113836314B (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN115099239B (en) | Resource identification method, device, equipment and storage medium | |
| US20210294969A1 (en) | Generation and population of new application document utilizing historical application documents | |
| CN114880498B (en) | Event information display method and device, equipment and medium | |
| CN114281981B (en) | News brief report generation method and device and electronic equipment | |
| CN114118049B (en) | Information acquisition method, device, electronic equipment and storage medium | |
| CN115563942A (en) | Contract generation method and device, electronic equipment and computer readable medium | |
| CN114118937A (en) | Information recommendation method and device based on task, electronic equipment and storage medium | |
| CN112989066A (en) | Data processing method and device, electronic equipment and computer readable medium | |
| CN115248890A (en) | User interest portrait generation method and device, electronic equipment and storage medium | |
| CN116069914B (en) | Training data generation method, model training method and device | |
| CN113377922B (en) | Method, device, electronic equipment and medium for matching information | |
| CN113010812B (en) | Information acquisition method, device, electronic equipment and storage medium | |
| CN111061854B (en) | Interaction method and device of intelligent conversation and electronic equipment | |
| EP4131022A1 (en) | Method and apparatus of determining location information, electronic device, storage medium, and program product | |
| CN114841755A (en) | Method and device for generating file, electronic equipment and storage medium | |
| CN116257690A (en) | Resource recommendation method and device, electronic equipment and storage medium | |
| CN117610580A (en) | Instruction identification method and device based on large model, electronic equipment and storage medium | |
| CN117762462A (en) | Code examination method, device, equipment and storage medium based on large model | |
| CN117453973A (en) | Information recommendation method, device, equipment and medium | |
| CN112288548A (en) | Method, device, medium and electronic equipment for extracting key information of target object | |
| CN113535857A (en) | Data synchronization method and device | |
| CN116842926A (en) | Template generation method and device, electronic equipment and storage medium | |
| CN117112728A (en) | Index query method, index query device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |