WO2022257840A1 - Information display method and apparatus, electronic device, and readable storage medium - Google Patents

Information display method and apparatus, electronic device, and readable storage medium Download PDF

Info

Publication number
WO2022257840A1
WO2022257840A1 PCT/CN2022/096729 CN2022096729W WO2022257840A1 WO 2022257840 A1 WO2022257840 A1 WO 2022257840A1 CN 2022096729 W CN2022096729 W CN 2022096729W WO 2022257840 A1 WO2022257840 A1 WO 2022257840A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
text
sentence
sentences
target reference
Prior art date
Application number
PCT/CN2022/096729
Other languages
French (fr)
Chinese (zh)
Inventor
罗达雄
时从斌
Original Assignee
维沃移动通信有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2022257840A1 publication Critical patent/WO2022257840A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/34Browsing; Visualisation therefor
    • G06F16/345Summarisation for human users
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • G06F40/211Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks

Definitions

  • the present application belongs to the technical field of data processing, and in particular relates to an information display method, device, electronic equipment and readable storage medium.
  • APP Application Program
  • the user can select the target reference text in the historical dialogue flow data, quote and reply to it, and the content of the reply and the target reference text will be displayed in a certain position in the dialogue flow in a certain structure.
  • the purpose of the embodiments of the present application is to provide an information display method, device, electronic device, and readable storage medium, which can solve the problem that the user cannot intuitively understand the content of the quoted text and the user experience is low.
  • the embodiment of the present application provides an information display method, the method includes:
  • an information display device comprising:
  • a determination module configured to determine the target reference text quoted by the user in the dialogue interface
  • a first calculation module configured to calculate a first score value of at least two sentences in the target reference text
  • the first selection module is used to select the target sentence whose first score value is higher than the score threshold in the at least two sentences as the abstract;
  • a display module configured to display the summary in the dialogue interface.
  • an embodiment of the present application provides an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored in the memory and operable on the processor, and the program or instruction is The processor realizes the steps of the information display method according to the first aspect when executed.
  • an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the information display method as described in the first aspect is implemented A step of.
  • the embodiment of the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions, so as to implement the first aspect The steps of the information display method.
  • an embodiment of the present application provides a computer program product, where the computer program product is executed by at least one processor to implement the steps of the information display method described in the first aspect.
  • the embodiment of the present application provides an electronic device configured to execute the steps of the information display method described in the first aspect.
  • the target reference text quoted by the user in the dialogue interface is determined, the first score value of at least two sentences in the target reference text is calculated, and the first score value of at least two sentences is selected to be higher than the score threshold
  • the target sentence of is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the extracted abstract More accurate and more relevant to the gist of the target cited text.
  • FIG. 1 shows a schematic flowchart of an information display method provided by an embodiment of the present application
  • FIG. 2A shows a schematic flowchart of an information display method provided by an embodiment of the present application
  • FIG. 2B shows a schematic flow chart of an information display method provided by an embodiment of the present application
  • FIG. 3A and FIG. 3B show a schematic diagram of an abstract extraction operation provided by the embodiment of the present application
  • FIG. 4 shows a schematic flow chart of an information display method provided by an embodiment of the present application
  • FIG. 5A and FIG. 5B show a schematic diagram of an abstract extraction operation provided by the embodiment of the present application
  • FIG. 6 shows a schematic flowchart of an information display method provided by an embodiment of the present application.
  • FIG. 7A to FIG. 7C show a schematic diagram of an abstract extraction operation provided by the embodiment of the present application.
  • FIG. 8 shows a schematic flowchart of an information display method provided by an embodiment of the present application.
  • FIG. 9 shows a schematic structural diagram of an information display device provided by an embodiment of the present application.
  • FIG. 10 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 11 shows a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present application.
  • FIG. 1 shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be executed by software or hardware installed in the terminal device. As shown in Fig. 1, the method may include the following steps.
  • S110 Determine the target reference text quoted by the user in the dialogue interface.
  • the user uses the dialogue interface of the electronic device for text interaction
  • at least part of the text in the dialogue interface may be quoted as the target reference text.
  • S111 Calculate first score values of at least two sentences in the target reference text.
  • the target reference text includes multiple sentences, where each sentence can be used as a summary, and the first score value can reflect the probability of a sentence as a summary. The higher the first score, the higher the probability of a sentence as a summary. Bigger, more in line with the gist of the target citation text.
  • the at least two sentences in the target reference text can be any sentences in the target reference text.
  • S112 Select a target sentence whose first score value is higher than a score threshold among at least two sentences as a summary.
  • the target sentence has a higher probability of being a summary, which can better reflect the main meaning of the target reference text, and is convenient for users to intuitively understand the target reference.
  • the content of the text improves the user experience.
  • the content of the summary is completely displayed in the dialogue interface.
  • an information display method in an embodiment of the present application determines the target reference text quoted by the user in the dialog interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score value of at least two sentences in the target reference text.
  • the target sentence whose score value is higher than the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the extracted abstract More accurate and more relevant to the gist of the target cited text.
  • the information display method before calculating the first score values of at least two sentences in the target reference text, the information display method further includes: calculating the probability of extracting the abstract of the target reference text, and using the first When the probability of extracting the abstract by the first extraction method is greater than the probability of extracting the abstract by the second extraction method, the first score value of at least two sentences in the target reference text is calculated.
  • the abstract can be extracted by extracting sentences (the first extraction method); when the target reference text is a text of a specific scene, Such as meeting scenarios, life payment scenarios, travel scenarios (airplane tickets, train tickets, hotels, banks, etc.), verification code scenarios, express delivery scenarios, movie scenarios, and operator scenarios, etc., you can use the method of extracting key fields (second Extract method) to extract the summary.
  • Extracting summaries from target citation texts can be based on summarization extraction models.
  • the first layer of the model segments the target reference text by characters
  • the second to sixth layers of the model model the semantic representation of the target reference text
  • the seventh to eighth layers of the model perform semantic representation
  • the target citation text for abstract extraction Specifically, task Task1 is used to judge the type of the target reference text and determine the extraction method of extracting the summary
  • task Task2 is used to extract key sentences from the target reference text as a summary in the first extraction method
  • task Task3 is used to use
  • the second extraction method extracts key fields from the target reference text as a summary.
  • the resulting task loss can be used as the input of the model to optimize the model.
  • the Token1 and Token2 of the first layer are used as the input vector of the target reference text (the input vector is the word vector after character segmentation), and CLS indicates the beginning of the target reference text.
  • the Embedding of the second layer encodes the input vector of the first layer, thereby converting the natural language of the high-dimensional semantic space into a low-dimensional vector space.
  • the Multi-Head-Self-Attention of the third layer is a multi-head attention mechanism.
  • Multi-Head-Self-Attention is used to analyze the literal meaning of the word vector, and input the Embedding encoded word vector to the third layer.
  • Multi-Head-Self-Attention multiple vector representations of the current word vector are obtained, and then concatenated and output to the fourth to sixth layers.
  • Add&BN and FFN are deep residual networks, which are used to convert the third After the output of the layer and the third layer is summed and regularized to obtain the decoding vector, the decoding vector is linearly mapped to the entire dictionary space, and then the softmax function is used to regularize the probability distribution of the dictionary vocabulary, that is, the score of each word, Then select the word with the highest score as the semantic representation of each word, and as the input of the seventh and eighth layers.
  • the seventh layer inputs the target reference text for semantic representation into Task1, Task2 and Task3, executes their respective tasks, and extracts the summary in the target reference text.
  • the key fields may be meeting time, meeting subject, and the like.
  • the key fields can be account name, account number, etc.
  • the key fields can be flight time, flight number, train number, departure time, hotel address, check-in time, loan account, account appointment, etc.
  • the key field can be the verification code number, etc.
  • the key fields can be the pick-up code, pick-up time, etc.
  • the key fields can be movie name, theater address, etc.
  • the method is as follows: use the feed-forward neural network to process the target reference text after semantic representation, and obtain a two-dimensional representation of the target reference text. vector.
  • the two-dimensional vector can be recorded as classify.
  • classify[0] represents the probability that the text type of the target reference text is suitable for extracting the abstract by extracting sentences (the first extraction method), and classify[1] represents the target
  • the text type of the reference text is suitable for the probability of extracting the abstract by means of extracting key fields (the second extraction method), and the extraction method with a higher probability is selected as the extraction method of the target reference text.
  • the probability that the text type of the meeting notice content is suitable for extracting the abstract by extracting sentences is 0.2
  • the text type of the meeting notice content is suitable for extracting keywords
  • the probability of extracting the summary by paragraph is 0.8, then the content of the conference notice is extracted by extracting key fields.
  • FIG. 2A shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be executed by software or hardware installed in the terminal device. As shown in Fig. 2A, the method may include the following steps.
  • S210 Determine the target reference text quoted by the user in the dialogue interface.
  • the abstract can be extracted by extracting sentences.
  • S211 Semantically represent at least two sentences in the target reference text.
  • the target reference text is segmented according to characters, and then the target reference text is semantically represented through the Bert language model.
  • S212 Perform mean value processing on at least two sentences after performing semantic representation to obtain a processed sentence.
  • S214 Select a target sentence whose first score value is higher than the score threshold among at least two sentences as the summary.
  • the content of the summary is completely displayed in the dialogue interface.
  • the target reference text quoted by the user in the dialogue interface is determined, the first score value of at least two sentences in the target reference text is calculated, and the first score value of at least two sentences is selected to be higher than the score threshold
  • the target sentence of is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the extracted abstract More accurate and more relevant to the gist of the target cited text.
  • FIG. 2B shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be executed by software or hardware installed in the terminal device. As shown in Fig. 2B, the method may include the following steps.
  • S220 Determine the target reference text quoted by the user in the dialogue interface.
  • the abstract can be extracted by extracting sentences.
  • S221 Calculate first score values of at least two sentences in the target reference text.
  • S223 Calculate a second score value of the combined sentence according to the first score value.
  • the first score value of each sentence in each combined sentence can be superimposed on each other to obtain the second score value of each combined sentence, or the forward neural network can be used to calculate Each combined sentence serves as the second score value of the summary.
  • S224 Select at least one target combined sentence whose second score value is higher than the score threshold from the multiple combined sentences as the target sentence, wherein the length of the target sentence does not exceed the display length threshold.
  • each second score value Arrange each second score value in descending order, first select the combined sentence corresponding to the highest second score value, and then judge whether the length of the combined sentence does not exceed the display length threshold, if not, then use the highest second score value
  • the sentence corresponding to the value is used as the target combination sentence. If it exceeds, select the second combination sentence and judge whether the length of the combination sentence does not exceed the display length threshold, and so on until the second combination sentence with the highest score value is found.
  • the target combination sentence whose length does not exceed the display length threshold is used as the target combination sentence.
  • multiple target combination sentences can also be selected as the abstract, specifically, the sentence length of a single sentence and the accumulated sentence length of multiple target combination sentences do not exceed the text length threshold, and the second score value of each target combination sentence is higher than The second score value of the remaining other combined sentences.
  • the number of words corresponds to the text length of the target reference text, the more words, the longer the text length, and the fewer the words, the shorter the text length.
  • the dialog interface it has a maximum limit on the number of displayed text characters, which can be determined by a display length threshold, and the display length threshold can be the maximum number of characters displayed on the dialog interface. For example, if the target reference text has 50 characters and the display length threshold is 30, the target reference text can display the first to 30th characters at most in the dialog interface.
  • the summary summarizes the main content of the target reference text, and the text length of the summary does not exceed the display length threshold, so that it can be completely displayed in the dialogue interface, which is convenient for users Understand the summarization extraction content of the target citation text.
  • the text 30 is displayed in the dialogue interface of the electronic device, and the type of the text 30 is a report text of the news class.
  • the user clicks or presses the text 30 it means that the text is quoted by the user in the dialogue interface.
  • Target Citation Text 30 is displayed in the dialogue interface of the electronic device.
  • the probability of classify[0] is greater than the probability of classify[1], indicating that the text type of the target reference text 30 is applicable
  • the abstract is extracted by means of extracting sentences (the first extraction method)
  • the key sentence is extracted as an abstract according to steps S211 to S217 from the target reference text 30 through the task Task2
  • the abstract 31 is displayed in the dialogue interface of the electronic device.
  • the user can also make a reply based on the displayed summary 31 , and the content of the reply can be displayed at 32 above the summary 31 to indicate the correspondence between the summary 31 and the content of the reply.
  • an information display method in an embodiment of the present application determines the target reference text quoted by the user in the dialog interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score value of at least two sentences in the target reference text.
  • the target sentence whose score value is higher than the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the extracted abstract More accurate and more relevant to the gist of the target cited text.
  • FIG. 4 shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be implemented by software or hardware installed in the terminal device. As shown in Fig. 4, the method may include the following steps.
  • S410 Determine the target reference text quoted by the user in the dialogue interface.
  • the abstract can be extracted by extracting key fields.
  • the reference text 50 of the meeting scene displayed in the dialog interface when the user clicks or long presses the position of the reference text 50, it means that the reference text 50 is the target reference text quoted by the user in the dialog interface.
  • S411 Perform semantic representation on the target reference text.
  • the target reference text is segmented according to characters, and then the target reference text is semantically represented through the Bert language model.
  • S412 Determine tags in the target reference text.
  • the target reference text of the conference scene shown in the dialog interface shown in Figure 5A is determined by the forward neural network to include the tags contained in the reference text as the conference time, conference location and conference topic.
  • the corresponding relationship between the meeting time label and the corresponding key field is: meeting time-this afternoon, meeting Time - 14:30. Extract all the key fields corresponding to the meeting time, and obtain the key field under the meeting time label as 14:30 this afternoon.
  • the key field of the meeting location label is XX Century City
  • the key field of the meeting theme label is the newcomer training meeting.
  • S414 Determine the label and the key field as an abstract, and the length of the abstract does not exceed a display length threshold.
  • the number of words corresponds to the text length of the target citation text, the more the number of words, the longer the text length, and the fewer the words, the shorter the text length.
  • the dialog interface it has a maximum limit on the number of displayed text characters, which can be determined by a display length threshold, and the display length threshold can be the maximum number of characters displayed on the dialog interface. For example, if the target reference text has 50 characters and the display length threshold is 30, the target reference text can display the first to 30th characters at most in the dialog interface.
  • the summary summarizes the main content of the target reference text, and the text length of the summary does not exceed the display length threshold, so that it can be completely displayed in the dialogue interface, which is convenient for users Understand the summarization extraction content of the target citation text.
  • the probability of classify[0] is less than the probability of classify[1], indicating that the target reference
  • the text type of the text 30 is suitable for extracting abstracts by means of extracting key fields (the second extraction method). Therefore, after the tags and key fields are extracted according to steps S411 to S414 through task Task3, the meeting theme and newcomer training The meeting is used as the first line of summary 51, the meeting time and 14:30 this afternoon are used as the second line of summary 51, and the meeting location and XX Century City are displayed in the dialogue interface as the third line of summary 51.
  • the user can also make a reply based on the displayed summary 51 , and the content of the reply can be displayed at 52 above the summary 51 to indicate the correspondence between the summary 51 and the content of the reply.
  • an information display method in an embodiment of the present application determines the target reference text quoted by the user in the dialog interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score value of at least two sentences in the target reference text.
  • the target sentence whose score value is higher than the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the extracted abstract More accurate and more relevant to the gist of the target cited text.
  • FIG. 6 shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be implemented by software or hardware installed in the terminal device. As shown in Fig. 6, the method may include the following steps.
  • S610 Determine the target reference text quoted by the user in the dialogue interface.
  • S611 Calculate first score values of at least two sentences in the target reference text.
  • S612 Select a target sentence whose first score value is higher than a score threshold among at least two sentences as a summary.
  • S610-S613 have the same or similar implementation manners as S110-S113 in the embodiment in FIG. 1 , which can be referred to each other, and will not be described again in this embodiment of the present application.
  • S614 Select a plurality of associated texts associated with the target reference text within a predetermined time period.
  • S615 Perform correlation analysis on the target reference text and the associated text to be selected to obtain a correlation degree.
  • the predetermined time may be any time period, such as 6 hours.
  • the target reference text and the associated text can be combined one-to-one, and then the Bert language model is used to semantically represent the target reference text and the associated text, and the target The semantic representation of the quoted text is recorded as H1, and the semantic representation of the associated text is recorded as H2.
  • H1 and H2 are expressed as vectors after being processed by the Bert language model, and then the following fusion strategy is used to fuse H1 and H2, specifically:
  • H1*H2 means multiplication of vectors, that is, character exchange between H1 and H2
  • H1-H2 means eliminating the same in H1 and H2 characters
  • Fusion represents the fused semantic representation.
  • the threshold may be determined according to the actual situation, which is not limited in this embodiment of the present application.
  • S617 In response to the trigger operation on the summary, jump from the position where the summary is displayed on the dialog interface to the position where the target associated text is located.
  • the target associated texts related to the meeting notification are selected as associated text 1, associated text 2 and associated text 3 according to step S613, as shown in Figure 7A, when the user clicks Or long press the position of the abstract 51 to display the floating list 70.
  • the associated tags of the target associated text are displayed.
  • the associated tags can be ranked according to the value of the degree of association, and the associated text with the highest degree of association is marked as Correlation 1, and so on are correlation 2 and correlation 3.
  • the method further includes:
  • the position of the summary 51 displayed on the dialogue interface will directly jump to the original position of the target reference text 50 .
  • An information display method which determines the target reference text quoted by the user in the dialogue interface, calculates the first score value of at least two sentences in the target reference text, and selects the first score value of at least two sentences
  • the target sentence above the score threshold is used as a summary, and the summary is displayed in the dialog interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the extracted abstract More accurate and more relevant to the gist of the target cited text.
  • the position where the summary is displayed on the dialogue interface can directly jump to the position of the target related information, providing the user with a link between the target reference text and the context.
  • Link information so as to achieve the purpose of linking the target reference text with the following text, enhance the user's understanding of the target reference text, and further improve the user experience.
  • the position where the abstract is displayed on the dialogue interface can directly jump to the original position of the target reference text, which can facilitate the user to read the complete content of the target reference text and enhance the user's understanding of the target reference text , to further enhance the user experience.
  • the execution subject may be an information display device, or a control module in the information display device for executing the information display method.
  • the information display device provided in the embodiment of the present application is described by taking the information display device executing the information display method as an example.
  • FIG. 9 shows a schematic structural diagram of an information display device provided by an embodiment of the present application.
  • the device 900 includes: a determination module 910 , a first calculation module 920 , a first selection module 930 and a display module 940 .
  • the determination module 910 is used to determine the target reference text quoted by the user in the dialogue interface.
  • the first calculation module 920 is used to calculate the first score values of at least two sentences in the target reference text.
  • the first selection module 930 is configured to select a target sentence whose first score value is higher than a score threshold among the at least two sentences as an abstract.
  • the display module 940 is used for displaying the summary in the dialogue interface.
  • An information display device determines the target reference text quoted by the user in the dialogue interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score of at least two sentences Target sentences whose values are higher than the score threshold are used as summaries, and the summaries are displayed in the dialog interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the first computing module 920 includes:
  • a semantic representation unit configured to perform semantic representation on at least two sentences in the target reference text.
  • the processing unit is configured to perform mean value processing on at least two sentences after performing semantic representation to obtain a processed sentence.
  • a first calculation unit configured to calculate the first score value of the processed sentence.
  • the first selecting module 930 includes: a combining unit, configured to combine the sentences to obtain a combined sentence.
  • a second calculation unit configured to calculate a second score value of the combined sentence according to the first score value.
  • a selecting unit configured to select at least one target combined sentence whose second score value is higher than a score threshold from a plurality of combined sentences as the target sentence, wherein the length of the target sentence does not exceed the displayed length threshold.
  • the apparatus 900 further includes: a second selecting module, configured to select a plurality of associated texts to be selected associated with the target quoted text within a predetermined time.
  • An analysis module configured to perform a correlation analysis on the target reference text and the associated text to be selected to obtain a degree of correlation.
  • the ranking module is used to rank each degree of association, and select the candidate association text whose ranking meets the requirements as the target association text.
  • the first jumping module is configured to jump from the position where the summary is displayed on the dialog interface to the position where the target associated text is located in response to a trigger operation on the summary.
  • the apparatus 900 further includes: a second jump module (not shown in the figure).
  • the second jumping module is configured to jump from the position where the summary is displayed on the dialog interface to the position where the target reference text is located in response to a trigger operation on the summary.
  • the device 900 provided in the embodiment of the present application can execute the methods in the foregoing method embodiments, and realize the functions and beneficial effects of the methods in the foregoing method embodiments, which will not be repeated here.
  • the information display device in the embodiment of the present application may be a device, or a component, an integrated circuit, or a chip in a terminal.
  • the device may be a mobile electronic device or a non-mobile electronic device.
  • the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant).
  • non-mobile electronic devices can be servers, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (television, TV), teller machine or self-service machine, etc., this application Examples are not specifically limited.
  • Network Attached Storage NAS
  • personal computer personal computer, PC
  • television television
  • teller machine or self-service machine etc.
  • the information display device in the embodiment of the present application may be a device with an operating system.
  • the operating system may be an Android operating system, an ios operating system, or other possible operating systems, which are not specifically limited in this embodiment of the present application.
  • the information display device provided by the embodiment of the present application can realize various processes realized by the method embodiments in FIG. 1 to FIG. 8 , and details are not repeated here to avoid repetition.
  • the embodiment of the present application also provides an electronic device 100, including a processor 101, a memory 102, and a program or instruction stored in the memory 102 and operable on the processor 101.
  • the program when the instructions are executed by the processor 101, each process of the above-mentioned information display method embodiment can be realized, and the same technical effect can be achieved. To avoid repetition, details are not repeated here.
  • FIG. 11 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.
  • the electronic device 1000 includes, but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010, etc. part.
  • the electronic device 1000 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 1010 through the power management system, so that the management of charging, discharging, and function can be realized through the power management system. Consumption management and other functions.
  • a power supply such as a battery
  • the structure of the electronic device shown in FIG. 11 does not constitute a limitation to the electronic device.
  • the electronic device may include more or fewer components than shown in the figure, or combine some components, or arrange different components, and details will not be repeated here. .
  • the user input unit 1007 is used to determine the target reference text quoted by the user in the dialogue interface, and the processor 1010 is used to calculate the first score value of at least two sentences in the target reference text, and select the at least two sentences The target sentence whose first score value is higher than the score threshold is used as a summary, and the display unit 1006 displays the summary in the dialogue interface.
  • the processor 1010 is further configured to semantically represent at least two sentences in the target reference text. At least two sentences after semantic representation are averaged to obtain the processed sentence. Calculating a first score value of the processed sentence.
  • the processor 1010 is further configured to combine the sentences to obtain a combined sentence. calculating a second score value of the combined sentence according to the first score value. Selecting at least one target combined sentence whose second score value is higher than a score threshold from a plurality of combined sentences is selected as the target sentence, wherein the length of the target sentence does not exceed the display length threshold.
  • the processor 1010 is further configured to select a plurality of candidate associated texts associated with the target referenced text within a predetermined time period.
  • a correlation analysis is performed on the target reference text and the associated text to be selected to obtain a correlation degree. Rank each of the related degrees, and select the candidate related text whose ranking meets the requirements as the target related text.
  • the dialogue interface displays a position where the summary is displayed and jumps to a position where the target associated text is located.
  • the processor 1010 is further configured to, in response to a trigger operation on the summary, jump from the position where the summary is displayed on the dialogue interface to the position where the target reference text is located.
  • the radio frequency unit 1001 can be used for sending and receiving information or receiving and sending signals during a call. Specifically, after receiving downlink data from the base station, it is processed by the processor 1010; in addition, the uplink data is sent to the base station.
  • the radio frequency unit 1001 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
  • the radio frequency unit 1001 can also communicate with the network and other devices through a wireless communication system.
  • the electronic device provides users with wireless broadband Internet access through the network module 1002, such as helping users send and receive emails, browse web pages, and access streaming media.
  • the audio output unit 1003 may convert audio data received by the radio frequency unit 1001 or the network module 1002 or stored in the memory 1009 into an audio signal and output as sound.
  • the audio output unit 1003 includes a speaker, a buzzer, a receiver, and the like.
  • the input unit 1004 may include a graphics processor (Graphics Processing Unit, GPU) 10041 and a microphone 10042, and the graphics processor 10041 is used for the image capture device (such as the image data of the still picture or video obtained by the camera) for processing.
  • a graphics processor Graphics Processing Unit, GPU
  • the graphics processor 10041 is used for the image capture device (such as the image data of the still picture or video obtained by the camera) for processing.
  • the display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 1007 includes a touch panel 10071 and other input devices 10072 .
  • the touch panel 10071 is also called a touch screen.
  • the touch panel 10071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, and joysticks, which will not be repeated here.
  • the memory 1009 can be used to store software programs as well as various data, including but not limited to application programs and operating systems.
  • Processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes operating systems, user interfaces, and application programs, and the modem processor mainly processes wireless communications. It can be understood that the foregoing modem processor may not be integrated into the processor 1010 .
  • the electronic device 1000 also includes at least one sensor 1005, such as a light sensor, a motion sensor, and other sensors.
  • the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 10061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 10061 and the / or backlighting.
  • the display unit 1006 is used for displaying information input by the user or information provided to the user (such as displaying a summary).
  • the display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like.
  • LCD Liquid Crystal Display
  • OLED Organic Light-Emitting Diode
  • the user input unit 1007 can be used to receive input numbers or character information, and generate key signal input related to user settings and function control of the electronic device.
  • the user input unit 1007 includes a touch panel 10071 and other input devices 10072 .
  • the touch panel 10071 also referred to as a touch screen, can collect touch operations of the user on or near it (for example, the user uses any suitable object or accessory such as a finger and a stylus on the touch panel 10071 or near the touch panel 10071 operate).
  • the touch panel 10071 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and sends it to the For the processor 1010, receive the command sent by the processor 1010 and execute it.
  • the touch panel 10071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave.
  • the user input unit 1007 may also include other input devices 10072 . Specifically, other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.
  • the touch panel 10071 can be covered on the display panel 10061, and when the touch panel 10071 detects a touch operation on or near it, it will be sent to the processor 1010 to determine the type of the touch event, and then the processor 1010 will The type of event provides a corresponding visual output on the display panel 10061.
  • the touch panel 10071 and the display panel 10061 are used as two independent components to realize the input and output functions of the electronic device, in some embodiments, the touch panel 10071 and the display panel 10061 can be integrated
  • the implementation of the input and output functions of the electronic device is not specifically limited here.
  • the interface unit 1008 is an interface for connecting an external device to the electronic device 1000 .
  • an external device may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, audio input/output (I/O) ports, video I/O ports, headphone ports, and more.
  • the interface unit 1008 can be used to receive input from an external device (for example, data information, power, etc.) transfer data between devices.
  • the memory 1009 can be used to store software programs as well as various data.
  • the memory 1009 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.); Data created by the use of mobile phones (such as audio data, phonebook, etc.), etc.
  • the memory 1009 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.
  • the processor 1010 is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device, by running or executing software programs and/or modules stored in the memory 1009, and calling data stored in the memory 1009 , to perform various functions of the electronic equipment and process data, so as to monitor the electronic equipment as a whole.
  • the processor 1010 may include one or more processing units; preferably, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem
  • the processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 1010 .
  • An electronic device which determines the target reference text quoted by the user in the dialogue interface, calculates the first score value of at least two sentences in the target reference text, and selects the first score value of the at least two sentences with the highest value
  • the target sentence above the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
  • the extracted abstract More accurate and more relevant to the gist of the target cited text.
  • the embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, each process of the above-mentioned information display method embodiment is realized, and the same technology can be achieved. Effect, in order to avoid repetition, will not repeat them here.
  • Readable storage media include computer readable storage media, such as computer read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, etc.
  • the embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, the processor is used to run programs or instructions, and realize the various processes of the above information display method embodiments, and can achieve the same Technical effects, in order to avoid repetition, will not be repeated here.
  • chips mentioned in the embodiments of the present application may also be called system-on-chip, system-on-chip, system-on-a-chip, or system-on-a-chip.
  • the embodiment of the present application further provides a computer program product, the computer program product is executed by at least one processor to implement the various processes of the above information display method embodiment, and can achieve the same technical effect, in order to avoid repetition, it is not repeated here Let me repeat.
  • the embodiment of the present application further provides an electronic device, which is configured to execute the processes of the foregoing information display method embodiments, and can achieve the same technical effect. To avoid repetition, details are not repeated here.
  • the term “comprising”, “comprising” or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase “comprising a " does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.
  • the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • User Interface Of Digital Computer (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

An information display method and apparatus, an electronic device, and a readable storage medium, which relate to the technical field of data processing. The method comprises: determining a target reference text referenced by a user in a dialogue interface (S110); calculating first score values of at least two sentences in the target reference text (S111); selecting a target sentence the first score value of which is higher than a score threshold value in the at least two sentences as an abstract (S112); and displaying the abstract in the dialogue interface (S113).

Description

信息显示方法、装置、电子设备及可读存储介质Information display method, device, electronic device and readable storage medium
交叉引用cross reference
本发明要求在2021年06月07日提交中国专利局、申请号为202110631105.7、发明名称为“信息显示方法、装置、电子设备及可读存储介质”的中国专利申请的优先权,该申请的全部内容通过引用结合在本发明中。The present invention claims the priority of the Chinese patent application submitted to the China Patent Office on June 07, 2021, with the application number 202110631105.7, and the title of the invention is "information display method, device, electronic equipment, and readable storage medium". The contents are incorporated herein by reference.
技术领域technical field
本申请属于数据处理技术领域,具体涉及一种信息显示方法、装置、电子设备及可读存储介质。The present application belongs to the technical field of data processing, and in particular relates to an information display method, device, electronic equipment and readable storage medium.
背景技术Background technique
目前,终端的应用程序(Application,APP)大多支持引用功能。例如,在社交APP中,用户可以在历史对话流数据中选择目标引用文本,对其引用并回复,回复的内容与目标引用文本会以某一种结构被显示在对话流的某一位置。At present, most application programs (Application, APP) of the terminal support the reference function. For example, in a social APP, the user can select the target reference text in the historical dialogue flow data, quote and reply to it, and the content of the reply and the target reference text will be displayed in a certain position in the dialogue flow in a certain structure.
在上述过程中,存在APP会自动将超出长度部分内容省略,点击之后才能显示完整的内容的情况,用户可能无法直观理解引用文本的内容,影响用户体验。In the above process, there is a situation that the APP will automatically omit the content exceeding the length, and the complete content can only be displayed after clicking. The user may not be able to intuitively understand the content of the quoted text, which will affect the user experience.
发明内容Contents of the invention
本申请实施例的目的是提供一种信息显示方法、装置、电子设备及可读存储介质,能够解决用户无法直观理解引用文本的内容,用户体验低的问题。The purpose of the embodiments of the present application is to provide an information display method, device, electronic device, and readable storage medium, which can solve the problem that the user cannot intuitively understand the content of the quoted text and the user experience is low.
第一方面,本申请实施例提供了一种信息显示方法,该方法包括:In the first aspect, the embodiment of the present application provides an information display method, the method includes:
确定用户在对话界面中引用的目标引用文本;Determining the target citation text that the user cites in the conversational interface;
计算所述目标引用文本中至少两个句子的第一得分值;calculating first score values of at least two sentences in the target reference text;
选取所述至少两个句子中所述第一得分值高于分数阈值的目标句子作为摘要;Selecting the target sentence whose first score value is higher than the score threshold in the at least two sentences as a summary;
在所述对话界面中显示所述摘要。displaying the summary in the dialogue interface.
第二方面,本申请实施例提供了一种信息显示装置,所述装置包括:In a second aspect, an embodiment of the present application provides an information display device, the device comprising:
确定模块,用于确定用户在对话界面中引用的目标引用文本;A determination module, configured to determine the target reference text quoted by the user in the dialogue interface;
第一计算模块,用于计算所述目标引用文本中至少两个句子的第一得分值;A first calculation module, configured to calculate a first score value of at least two sentences in the target reference text;
第一选取模块,用于选取所述至少两个句子中所述第一得分值高于分数阈值的目标句子作为摘要;The first selection module is used to select the target sentence whose first score value is higher than the score threshold in the at least two sentences as the abstract;
显示模块,用于在所述对话界面中显示所述摘要。A display module, configured to display the summary in the dialogue interface.
第三方面,本申请实施例提供了一种电子设备,该电子设备包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的信息显示方法的步骤。In a third aspect, an embodiment of the present application provides an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored in the memory and operable on the processor, and the program or instruction is The processor realizes the steps of the information display method according to the first aspect when executed.
第四方面,本申请实施例提供了一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如第一方面所述的信息显示方法的步骤。In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the information display method as described in the first aspect is implemented A step of.
第五方面,本申请实施例提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如第一方面所述的信息显示方法的步骤。In the fifth aspect, the embodiment of the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions, so as to implement the first aspect The steps of the information display method.
第六方面,本申请实施例提供了一种计算机程序产品,所述计算机程序产品被至少一个处理器执行以实现如第一方面所述的信息显示方法的步骤。In a sixth aspect, an embodiment of the present application provides a computer program product, where the computer program product is executed by at least one processor to implement the steps of the information display method described in the first aspect.
第七方面,本申请实施例提供了一种电子设备,所述电子设备被配置成用于执行如第一方面所述的信息显示方法的步骤。In a seventh aspect, the embodiment of the present application provides an electronic device configured to execute the steps of the information display method described in the first aspect.
在本申请实施例中,确定用户在对话界面中引用的目标引用文本,计算 目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。In the embodiment of the present application, the target reference text quoted by the user in the dialogue interface is determined, the first score value of at least two sentences in the target reference text is calculated, and the first score value of at least two sentences is selected to be higher than the score threshold The target sentence of is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
附图说明Description of drawings
图1示出本申请实施例提供的一种信息显示方法的一种流程示意图;FIG. 1 shows a schematic flowchart of an information display method provided by an embodiment of the present application;
图2A示出本申请实施例提供的一种信息显示方法的一种流程示意图;FIG. 2A shows a schematic flowchart of an information display method provided by an embodiment of the present application;
图2B示出本申请实施例提供的一种信息显示方法的一种流程示意图;FIG. 2B shows a schematic flow chart of an information display method provided by an embodiment of the present application;
图3A和图3B示出本申请实施例提供的一种摘要提取的操作示意图;FIG. 3A and FIG. 3B show a schematic diagram of an abstract extraction operation provided by the embodiment of the present application;
图4示出本申请实施例提供的一种信息显示方法的一种流程示意图;FIG. 4 shows a schematic flow chart of an information display method provided by an embodiment of the present application;
图5A和图5B示出本申请实施例提供的一种摘要提取的操作示意图;FIG. 5A and FIG. 5B show a schematic diagram of an abstract extraction operation provided by the embodiment of the present application;
图6示出本申请实施例提供的一种信息显示方法的一种流程示意图;FIG. 6 shows a schematic flowchart of an information display method provided by an embodiment of the present application;
图7A至图7C示出本申请实施例提供的一种摘要提取的操作示意图;FIG. 7A to FIG. 7C show a schematic diagram of an abstract extraction operation provided by the embodiment of the present application;
图8示出本申请实施例提供的一种信息显示方法的一种流程示意图;FIG. 8 shows a schematic flowchart of an information display method provided by an embodiment of the present application;
图9示出本申请实施例提供的一种信息显示装置的结构示意图;FIG. 9 shows a schematic structural diagram of an information display device provided by an embodiment of the present application;
图10示出本申请实施例提供的一种电子设备的结构示意图;FIG. 10 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application;
图11示出本申请实施例提供的一种电子设备的硬件结构示意图。FIG. 11 shows a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present application.
具体实施方式Detailed ways
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员获得的 所有其他实施例,都属于本申请保护的范围。The following will clearly describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in this application belong to the protection scope of this application.
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施,且“第一”、“第二”等所区分的对象通常为一类,并不限定对象的个数,例如第一对象可以是一个,也可以是多个。此外,说明书以及权利要求中“和/或”表示所连接对象的至少其中之一,字符“/”,一般表示前后关联对象是一种“或”的关系。The terms "first", "second" and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific sequence or sequence. It should be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application can be practiced in sequences other than those illustrated or described herein, and that references to "first," "second," etc. distinguish Objects are generally of one type, and the number of objects is not limited. For example, there may be one or more first objects. In addition, "and/or" in the specification and claims means at least one of the connected objects, and the character "/" generally means that the related objects are an "or" relationship.
下面结合附图,通过具体的实施例及其应用场景对本申请实施例提供的信息显示方法进行详细地说明。The information display method provided by the embodiment of the present application will be described in detail below through specific embodiments and application scenarios with reference to the accompanying drawings.
图1示出本申请实施例提供的一种信息显示方法的一种流程示意图,该方法可以由电子设备执行,例如终端设备。也就是说,上述的信息显示方法可以由安装在终端设备的软件或硬件来执行。如图1所示,该方法可以包括以下步骤。FIG. 1 shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be executed by software or hardware installed in the terminal device. As shown in Fig. 1, the method may include the following steps.
S110:确定用户在对话界面中引用的目标引用文本。S110: Determine the target reference text quoted by the user in the dialogue interface.
在用户使用电子设备的对话界面进行文本交互时,可以引用该对话界面中的至少部分文本作为目标引用文本。例如用户通过电子设备的屏幕在对话界面中点击或长按该目标引用文本,该目标引用文本则作为引用的文本。When the user uses the dialogue interface of the electronic device for text interaction, at least part of the text in the dialogue interface may be quoted as the target reference text. For example, the user clicks or long presses the target reference text in the dialogue interface through the screen of the electronic device, and the target reference text is used as the reference text.
S111:计算目标引用文本中至少两个句子的第一得分值。S111: Calculate first score values of at least two sentences in the target reference text.
具体来讲,目标引用文本中包括多个句子,其中,每个句子都可以作为摘要,第一得分值可以体现出句子作为摘要的概率,第一分值越高,句子作为摘要的概率越大,与目标引用文本的主旨更切合。目标引用文本中的至少两个句子可以是目标引用文本中任意的句子,在计算至少两个句子的第一得分值时,可以首先对至少两个句子进行语义表示,然后对进行语义表示后的 句子进行均值化处理,最后利用前向神经网络计算进行均值化处理后的句子的第一得分值。Specifically, the target reference text includes multiple sentences, where each sentence can be used as a summary, and the first score value can reflect the probability of a sentence as a summary. The higher the first score, the higher the probability of a sentence as a summary. Bigger, more in line with the gist of the target citation text. The at least two sentences in the target reference text can be any sentences in the target reference text. When calculating the first score value of the at least two sentences, the semantic representation of the at least two sentences can be performed first, and then after the semantic representation Sentences are averaged, and finally the first score value of the sentence after the average processing is calculated by using the forward neural network.
S112:选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要。S112: Select a target sentence whose first score value is higher than a score threshold among at least two sentences as a summary.
具体来讲,至少两个句子的第一得分值高于分数阈值时,说明该目标句子作为摘要的概率较大,其更能反应出目标引用文本的主旨含义,便于用户直观的了解目标引用文本的内容,提升了用户体验感。Specifically, when the first score value of at least two sentences is higher than the score threshold, it indicates that the target sentence has a higher probability of being a summary, which can better reflect the main meaning of the target reference text, and is convenient for users to intuitively understand the target reference. The content of the text improves the user experience.
S113:在对话界面中显示摘要。S113: Display the summary in the dialogue interface.
具体来讲,在对话界面中完整的显示摘要的内容。Specifically, the content of the summary is completely displayed in the dialogue interface.
由此,本申请实施例的一种信息显示方法,确定用户在对话界面中引用的目标引用文本,计算目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。Thus, an information display method in an embodiment of the present application determines the target reference text quoted by the user in the dialog interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score value of at least two sentences in the target reference text. The target sentence whose score value is higher than the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
在一种可能的实现方式中,在计算目标引用文本中至少两个句子的第一得分值之前,信息显示方法还包括:计算对目标引用文本进行摘要提取的提取方式的概率,在采用第一提取方式提取摘要的概率大于采用第二提取方式提取摘要的概率的情况下,计算目标引用文本中至少两个句子的第一得分值。具体来讲,对于目标引用文本为新闻类的报道性文本、产品的说明性文本等时,可以采用提取句子的方式(第一提取方式)提取摘要,对于目标引用文本为特定场景的文本时,如会议场景、生活缴费场景、出行场景(飞机票、火车票、酒店、银行等)、验证码场景、快递场景、电影场景以及运营商场景等时,可以采取提取关键字段的方 式(第二提取方式)提取摘要。In a possible implementation manner, before calculating the first score values of at least two sentences in the target reference text, the information display method further includes: calculating the probability of extracting the abstract of the target reference text, and using the first When the probability of extracting the abstract by the first extraction method is greater than the probability of extracting the abstract by the second extraction method, the first score value of at least two sentences in the target reference text is calculated. Specifically, when the target reference text is news report text, product explanatory text, etc., the abstract can be extracted by extracting sentences (the first extraction method); when the target reference text is a text of a specific scene, Such as meeting scenarios, life payment scenarios, travel scenarios (airplane tickets, train tickets, hotels, banks, etc.), verification code scenarios, express delivery scenarios, movie scenarios, and operator scenarios, etc., you can use the method of extracting key fields (second Extract method) to extract the summary.
从目标引用文本中提取摘要可以基于摘要提取模型进行提取。其中,该模型的第一层对目标引用文本按字符切分,该模型的第二层至第六层建模目标引用文本的语义表示,该模型的七层至第八层对进行语义表示后的目标引用文本进行摘要提取。具体来说,任务Task1用于对目标引用文本的类型进行判断并确定提取摘要的提取方式,任务Task2用于以第一提取方式从目标引用文本中提取关键的句子作为摘要,任务Task3用于以第二提取方式从目标引用文本中提取关键字段作为摘要。对于该模型的优化,可以将任务Task1、任务Task2以及任务Task3三个任务执行后,产生的任务损失可以再作为该模型的输入对该模型进行优化。Extracting summaries from target citation texts can be based on summarization extraction models. Among them, the first layer of the model segments the target reference text by characters, the second to sixth layers of the model model the semantic representation of the target reference text, and the seventh to eighth layers of the model perform semantic representation The target citation text for abstract extraction. Specifically, task Task1 is used to judge the type of the target reference text and determine the extraction method of extracting the summary, task Task2 is used to extract key sentences from the target reference text as a summary in the first extraction method, and task Task3 is used to use The second extraction method extracts key fields from the target reference text as a summary. For the optimization of this model, after the three tasks of task Task1, task Task2 and task Task3 are executed, the resulting task loss can be used as the input of the model to optimize the model.
具体来讲,第一层的Token1、Token2等作为目标引用文本的输入向量(输入向量为字符分割后的字词向量),CLS表示目标引用文本的开始。第二层的Embedding对第一层的输入向量进行编码,从而将高维语义空间的自然语言转换到低维的向量空间。Specifically, the Token1 and Token2 of the first layer are used as the input vector of the target reference text (the input vector is the word vector after character segmentation), and CLS indicates the beginning of the target reference text. The Embedding of the second layer encodes the input vector of the first layer, thereby converting the natural language of the high-dimensional semantic space into a low-dimensional vector space.
第三层的Multi-Head-Self-Attention为多头注意力机制,Multi-Head-Self-Attention用于解析字词向量的字面意思,将经过Embedding编码的字词向量输入到第三层的多个Multi-Head-Self-Attention中,得到当前字词向量的多个向量表征,然后拼接起来输出到第四层至第六层,其中,Add&BN和FFN为深度残差网络,其用于将第三层以及第三层的输出进行求和正则得到解码向量后,将解码向量经过线性映射,将其映射到整个字典空间,然后经过softmax函数规整成字典词汇的概率分布,即每个词的分数,之后选取分数最高的词作为每个字词的语义表示,并作为第七层和第八层的输入。第七层将进行语义表示的目标引用文本输入到任务Task1、任务Task2和任务Task3,执行各自的任务,提取目标引用文本中的摘要。The Multi-Head-Self-Attention of the third layer is a multi-head attention mechanism. Multi-Head-Self-Attention is used to analyze the literal meaning of the word vector, and input the Embedding encoded word vector to the third layer. In Multi-Head-Self-Attention, multiple vector representations of the current word vector are obtained, and then concatenated and output to the fourth to sixth layers. Among them, Add&BN and FFN are deep residual networks, which are used to convert the third After the output of the layer and the third layer is summed and regularized to obtain the decoding vector, the decoding vector is linearly mapped to the entire dictionary space, and then the softmax function is used to regularize the probability distribution of the dictionary vocabulary, that is, the score of each word, Then select the word with the highest score as the semantic representation of each word, and as the input of the seventh and eighth layers. The seventh layer inputs the target reference text for semantic representation into Task1, Task2 and Task3, executes their respective tasks, and extracts the summary in the target reference text.
具体来讲,对于特定场景文本类型中的会议场景而言,其关键字段可以为会议时间、会议主题等。对于生活缴费场景而言,其关键字段可 以为户名、户号等。对于出行场景而言,其关键字段可以为航班时间、航班号、车次、发车时间、酒店地址、入住时间、贷款账户、账户约等。对于验证码场景,关键字段可以为验证码号等。对于快递场景,关键字段可以为取货码、取件时间等。对于电影场景,关键字段可以为电影名、影院地址等。Specifically, for a meeting scene in a specific scene text type, its key fields may be meeting time, meeting subject, and the like. For the life payment scenario, the key fields can be account name, account number, etc. For travel scenarios, the key fields can be flight time, flight number, train number, departure time, hotel address, check-in time, loan account, account appointment, etc. For the verification code scenario, the key field can be the verification code number, etc. For the express delivery scenario, the key fields can be the pick-up code, pick-up time, etc. For a movie scene, the key fields can be movie name, theater address, etc.
更为具体的,对于任务Task1对目标引用文本的类型进行判断并确定摘要的提取方式具体为:采用前向神经网络对进行语义表示后的目标引用文本进行处理,得到目标引用文本的一个二维向量。该二维向量可以记为classify,classify[0]表示的是该目标引用文本的文本类型适用于采用提取句子的方式(第一提取方式)提取摘要的概率,classify[1]表示的是该目标引用文本的文本类型适用于采用提取关键字段的方式(第二提取方式)提取摘要的概率,选取概率较大的一者的提取方式作为该目标引用文本的提取方式。More specifically, for the task Task1 to judge the type of the target reference text and determine the extraction method of the abstract, the method is as follows: use the feed-forward neural network to process the target reference text after semantic representation, and obtain a two-dimensional representation of the target reference text. vector. The two-dimensional vector can be recorded as classify. classify[0] represents the probability that the text type of the target reference text is suitable for extracting the abstract by extracting sentences (the first extraction method), and classify[1] represents the target The text type of the reference text is suitable for the probability of extracting the abstract by means of extracting key fields (the second extraction method), and the extraction method with a higher probability is selected as the extraction method of the target reference text.
例如,将会议场景下的会议通知内容作为目标引用文本时,该会议通知内容的文本类型适用于采用提取句子的方式提取摘要的概率为0.2,该会议通知内容的文本类型适用于采用提取关键字段的方式提取摘要的概率为0.8,则该会议通知内容采用提取关键字段的方式提取摘要。For example, when the meeting notice content in the meeting scene is used as the target reference text, the probability that the text type of the meeting notice content is suitable for extracting the abstract by extracting sentences is 0.2, and the text type of the meeting notice content is suitable for extracting keywords The probability of extracting the summary by paragraph is 0.8, then the content of the conference notice is extracted by extracting key fields.
由此,通过本申请实施例提供的一种信息显示方法,针对不同的文本类型,以适应于该文本类型的目标引用文本的提取方式提取摘要,提取的摘要能更加主观的反应出目标引用文本的主要内容,便于用户了解目标引用文本的主要内容,进一步提升了用户的体验感。此外,在第一提取方式下,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,通过该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。Therefore, through an information display method provided by the embodiment of the present application, for different text types, abstracts are extracted in an extraction method suitable for the text type of the target reference text, and the extracted abstract can more subjectively reflect the target reference text The main content of the text is convenient for users to understand the main content of the target reference text, which further improves the user experience. In addition, in the first extraction method, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, through this abstract extraction method, the extracted Abstracts are more accurate and more relevant to the gist of the target cited text.
图2A示出本申请实施例提供的一种信息显示方法的一种流程示意图,该方法可以由电子设备执行,例如终端设备。也就是说,上述的信 息显示方法可以由安装在终端设备的软件或硬件来执行。如图2A所示,该方法可以包括以下步骤。FIG. 2A shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be executed by software or hardware installed in the terminal device. As shown in Fig. 2A, the method may include the following steps.
S210:确定用户在对话界面中引用的目标引用文本。S210: Determine the target reference text quoted by the user in the dialogue interface.
对于目标引用文本为新闻类的报道性文本、产品的说明性文本时,可以采用提取句子的方式提取摘要。When the target reference text is news report text or product explanatory text, the abstract can be extracted by extracting sentences.
在目标引用文本的文本长度超出对话界面对应的显示长度阈值的情况下,进入S211-S215。When the text length of the target reference text exceeds the corresponding display length threshold of the dialog interface, go to S211-S215.
S211:对目标引用文本中的至少两个句子进行语义表示。S211: Semantically represent at least two sentences in the target reference text.
对目标引用文本按照字符进行切分,再通过Bert语言模型对目标引用文本进行语义表示。The target reference text is segmented according to characters, and then the target reference text is semantically represented through the Bert language model.
S212:对进行语义表示后的至少两个句子进行均值化处理,得到处理后的句子。S212: Perform mean value processing on at least two sentences after performing semantic representation to obtain a processed sentence.
具体来讲,对进行语义表示后的每个句子进行均值化得到句子表示,具体记为S=[S1,...,Sk],其中,Sk指的是进行均值化处理后的第k句句子。Specifically, each sentence after the semantic representation is averaged to obtain a sentence representation, which is specifically recorded as S=[S1,...,Sk], where Sk refers to the kth sentence after the average processing sentence.
S213:计算处理后的句子的第一得分值。S213: Calculate the first score value of the processed sentence.
对上述进行均值化后的句子表示S=[S1,...,Sk]通过前向神经网络计算每个句子的第一得分值,记为Score=[Score1,...,Scorek],其中,Scorek表示进行均值化处理后的第k句句子作为摘要的得分值,其中,第一得分值越高,句子作为摘要的概率越大。Sentence representation S=[S1,...,Sk] calculated by the forward neural network for the above-mentioned averaged sentences is recorded as Score=[Score1,...,Scorek], Wherein, Scorek represents the score value of the kth sentence after the mean value processing is used as the summary, wherein the higher the first score value is, the greater the probability of the sentence being used as the summary.
S214:选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要。S214: Select a target sentence whose first score value is higher than the score threshold among at least two sentences as the summary.
S215:在对话界面中显示摘要。S215: Display the summary in the dialogue interface.
具体来讲,在对话界面中完整的显示摘要的内容。Specifically, the content of the summary is completely displayed in the dialogue interface.
在本申请实施例中,确定用户在对话界面中引用的目标引用文本,计算目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申 请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。In the embodiment of the present application, the target reference text quoted by the user in the dialogue interface is determined, the first score value of at least two sentences in the target reference text is calculated, and the first score value of at least two sentences is selected to be higher than the score threshold The target sentence of is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
图2B示出本申请实施例提供的一种信息显示方法的一种流程示意图,该方法可以由电子设备执行,例如终端设备。也就是说,上述的信息显示方法可以由安装在终端设备的软件或硬件来执行。如图2B所示,该方法可以包括以下步骤。FIG. 2B shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be executed by software or hardware installed in the terminal device. As shown in Fig. 2B, the method may include the following steps.
S220:确定用户在对话界面中引用的目标引用文本。S220: Determine the target reference text quoted by the user in the dialogue interface.
对于目标引用文本为新闻类的报道性文本、产品的说明性文本时,可以采用提取句子的方式提取摘要。When the target reference text is news report text or product explanatory text, the abstract can be extracted by extracting sentences.
S221:计算目标引用文本中至少两个句子的第一得分值。S221: Calculate first score values of at least two sentences in the target reference text.
S222:将句子进行组合,得到组合句子。S222: Combine the sentences to obtain a combined sentence.
对上述进行语义处理后的句子按照句子的顺序穷举所有可能的组合句子,如进行语义处理后的句子有3句,则将第1个句子和第2个句子作为一个组合句子,第2个句子和第3个句子作为一个组合句子,将第1个句子和第3个句子作为一个组合句子。Exhaustively enumerate all possible combined sentences according to the order of the sentences after the above semantic processing. If there are 3 sentences after the semantic processing, the first sentence and the second sentence are regarded as a combined sentence, and the second sentence and the third sentence as a combined sentence, and the first sentence and the third sentence as a combined sentence.
S223:根据第一得分值计算组合句子的第二得分值。S223: Calculate a second score value of the combined sentence according to the first score value.
对于第二得分值而言,可以将上述每个组合句子中每个句子的第一得分值互相叠加,得到每个组合句子的第二得分值,或者也可以采用前向神经网络计算每个组合句子作为摘要的第二得分值。For the second score value, the first score value of each sentence in each combined sentence can be superimposed on each other to obtain the second score value of each combined sentence, or the forward neural network can be used to calculate Each combined sentence serves as the second score value of the summary.
S224:从多个组合句子中选取第二得分值高于分数阈值的至少一个目标组合句子作为目标句子,其中,目标句子的长度不超过显示长度阈值。S224: Select at least one target combined sentence whose second score value is higher than the score threshold from the multiple combined sentences as the target sentence, wherein the length of the target sentence does not exceed the display length threshold.
对各个第二得分值进行降序排列,首先选取最高第二得分值对应的 组合句子,然后判断该组合句子的长度是否不超过显示长度阈值,如果未超过,则将该最高第二得分值对应的句子作为目标组合句子,如果超过,则选取排名第二的组合句子且判断该组合句子的长度是否不超过显示长度阈值,依次类推,直至找出第二得分值最高且组合句子的长度不超过显示长度阈值的目标组合句子作为目标组合句子。另外,还可以选取多个目标组合句子作为摘要,具体是多个目标组合句子的单个句子的句子长度以及累加的句子长度不超过文本长度阈值,且各目标组合句子的第二得分值高于剩余的其他组合句子的第二得分值。Arrange each second score value in descending order, first select the combined sentence corresponding to the highest second score value, and then judge whether the length of the combined sentence does not exceed the display length threshold, if not, then use the highest second score value The sentence corresponding to the value is used as the target combination sentence. If it exceeds, select the second combination sentence and judge whether the length of the combination sentence does not exceed the display length threshold, and so on until the second combination sentence with the highest score value is found. The target combination sentence whose length does not exceed the display length threshold is used as the target combination sentence. In addition, multiple target combination sentences can also be selected as the abstract, specifically, the sentence length of a single sentence and the accumulated sentence length of multiple target combination sentences do not exceed the text length threshold, and the second score value of each target combination sentence is higher than The second score value of the remaining other combined sentences.
进一步,对于目标引用文本而言,其字数的多少对应目标引用文本的文本长度,字数越多,文本长度越长,字数越少,文本长度越短。对于对话界面而言,其具有显示文本字数的最大限制,该最大限制可以通过显示长度阈值确定,显示长度阈值可以为对话界面显示的最多字数。如目标引用文本的字数为50字,显示长度阈值为30时,目标引用文本在对话界面中最多可以显示文本从头开始的第1个字至第30个字。如此,通过从目标引用文本中提取出关键信息作为摘要,该摘要概括了目标引用文本的主要内容,且该摘要的文本长度不超出显示长度阈值,从而能在对话界面中完整的展示,便于用户理解目标引用文本的摘要提取内容。Further, for the target reference text, the number of words corresponds to the text length of the target reference text, the more words, the longer the text length, and the fewer the words, the shorter the text length. For the dialog interface, it has a maximum limit on the number of displayed text characters, which can be determined by a display length threshold, and the display length threshold can be the maximum number of characters displayed on the dialog interface. For example, if the target reference text has 50 characters and the display length threshold is 30, the target reference text can display the first to 30th characters at most in the dialog interface. In this way, by extracting key information from the target reference text as a summary, the summary summarizes the main content of the target reference text, and the text length of the summary does not exceed the display length threshold, so that it can be completely displayed in the dialogue interface, which is convenient for users Understand the summarization extraction content of the target citation text.
S225:在对话界面中显示摘要。S225: Display the summary in the dialogue interface.
如图3A所示的,电子设备的对话界面中显示文本30,该文本30的类型为新闻类的报道性文本,当用户点击或长按文本30时表示该文本为用户在对话界面中引用的目标引用文本30。As shown in Figure 3A, the text 30 is displayed in the dialogue interface of the electronic device, and the type of the text 30 is a report text of the news class. When the user clicks or presses the text 30, it means that the text is quoted by the user in the dialogue interface. Target Citation Text 30.
如图3B所示的,作为目标引用文本30,当任务Task1对目标引用文本30的类型进行判断后,classify[0]的概率大于classify[1]的概率,表示目标引用文本30的文本类型适用于采用提取句子的方式(第一提取方式)提取摘要,因此,通过任务Task2对目标引用文本30按照步骤S211至S217提取关键性的句子作为摘要,并在电子设备的对话界面中显示摘要 31。用户还可以基于显示的摘要31进行回复,回复的内容可以显示在摘要31的上方32处以表示摘要31和回复内容之间的对应关系。As shown in Figure 3B, as the target reference text 30, when the task Task1 judges the type of the target reference text 30, the probability of classify[0] is greater than the probability of classify[1], indicating that the text type of the target reference text 30 is applicable Since the abstract is extracted by means of extracting sentences (the first extraction method), the key sentence is extracted as an abstract according to steps S211 to S217 from the target reference text 30 through the task Task2, and the abstract 31 is displayed in the dialogue interface of the electronic device. The user can also make a reply based on the displayed summary 31 , and the content of the reply can be displayed at 32 above the summary 31 to indicate the correspondence between the summary 31 and the content of the reply.
由此,本申请实施例的一种信息显示方法,确定用户在对话界面中引用的目标引用文本,计算目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。Thus, an information display method in an embodiment of the present application determines the target reference text quoted by the user in the dialog interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score value of at least two sentences in the target reference text. The target sentence whose score value is higher than the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
图4示出本申请实施例提供的一种信息显示方法的一种流程示意图,该方法可以由电子设备执行,例如终端设备。也就是说,上述的信息显示方法可以由安装在终端设备的软件或硬件来执行。如图4所示,该方法可以包括以下步骤。FIG. 4 shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be implemented by software or hardware installed in the terminal device. As shown in Fig. 4, the method may include the following steps.
S410:确定用户在对话界面中引用的目标引用文本。S410: Determine the target reference text quoted by the user in the dialogue interface.
对于目标引用文本为典型场景的文本时,可以采用提取关键字段的方式提取摘要。如图5A所示的对话界面中显示的会议场景的引用文本50,当用户点击或长按引用文本50所在的位置,表示该引用文本50为用户在对话界面中引用的目标引用文本。When the target reference text is the text of a typical scene, the abstract can be extracted by extracting key fields. As shown in FIG. 5A , the reference text 50 of the meeting scene displayed in the dialog interface, when the user clicks or long presses the position of the reference text 50, it means that the reference text 50 is the target reference text quoted by the user in the dialog interface.
S411:对目标引用文本进行语义表示。S411: Perform semantic representation on the target reference text.
对目标引用文本按照字符进行切分,再通过Bert语言模型对目标引用文本进行语义表示。The target reference text is segmented according to characters, and then the target reference text is semantically represented through the Bert language model.
S412:确定目标引用文本中的标签。S412: Determine tags in the target reference text.
通过前向神经网络确定目标引用文本中每个词对应的标签,具体记为log it=[log it 1,...,log itn],其中,log itn表示的是第n个词对应的标签。Determine the label corresponding to each word in the target reference text through the forward neural network, specifically recorded as log it=[log it 1,...,log itn], where log itn represents the label corresponding to the nth word .
如图5A所示的对话界面中显示的会议场景的目标引用文本,通过 前向神经网络确定该引用文本中包含的标签为会议时间、会议地点和会议主题。The target reference text of the conference scene shown in the dialog interface shown in Figure 5A is determined by the forward neural network to include the tags contained in the reference text as the conference time, conference location and conference topic.
S413:基于标签提取关键字段。S413: Extract key fields based on tags.
将归属于每一个标签下的字段进行提取作为关键字段,还是以前述图5A所示的引用文本为例,会议时间标签与对应的关键字段的对应关系为:会议时间-今天下午,会议时间-14:30。将会议时间对应的关键字段都进行提取,得到会议时间标签下的关键字段为今天下午14:30。同理,会议地点标签的关键字段为某某世纪城,会议主题标签的关键字段为新人培训会议。Extract the fields belonging to each label as key fields, or take the reference text shown in Figure 5A above as an example, the corresponding relationship between the meeting time label and the corresponding key field is: meeting time-this afternoon, meeting Time - 14:30. Extract all the key fields corresponding to the meeting time, and obtain the key field under the meeting time label as 14:30 this afternoon. Similarly, the key field of the meeting location label is XX Century City, and the key field of the meeting theme label is the newcomer training meeting.
S414:将标签和关键字段确定为摘要,摘要的长度不超出显示长度阈值。S414: Determine the label and the key field as an abstract, and the length of the abstract does not exceed a display length threshold.
对于目标引用文本而言,其字数的多少对应目标引用文本的文本长度,字数越多,文本长度越长,字数越少,文本长度越短。对于对话界面而言,其具有显示文本字数的最大限制,该最大限制可以通过显示长度阈值确定,显示长度阈值可以为对话界面显示的最多字数。如目标引用文本的字数为50字,显示长度阈值为30时,目标引用文本在对话界面中最多可以显示文本从头开始的第1个字至第30个字。如此,通过从目标引用文本中提取出关键信息作为摘要,该摘要概括了目标引用文本的主要内容,且该摘要的文本长度不超出显示长度阈值,从而能在对话界面中完整的展示,便于用户理解目标引用文本的摘要提取内容。For the target citation text, the number of words corresponds to the text length of the target citation text, the more the number of words, the longer the text length, and the fewer the words, the shorter the text length. For the dialog interface, it has a maximum limit on the number of displayed text characters, which can be determined by a display length threshold, and the display length threshold can be the maximum number of characters displayed on the dialog interface. For example, if the target reference text has 50 characters and the display length threshold is 30, the target reference text can display the first to 30th characters at most in the dialog interface. In this way, by extracting key information from the target reference text as a summary, the summary summarizes the main content of the target reference text, and the text length of the summary does not exceed the display length threshold, so that it can be completely displayed in the dialogue interface, which is convenient for users Understand the summarization extraction content of the target citation text.
S415:在对话界面中显示摘要。S415: Display the summary in the dialogue interface.
如图5B所示的,在对图5A所示的目标引用文本50,当任务Task1对目标引用文本30的类型进行判断后,classify[0]的概率小于classify[1]的概率,表示目标引用文本30的文本类型适用于采用提取关键字段的方式(第二提取方式)提取摘要,因此,通过任务Task3按照步骤S411至S414的方式提取出标签和关键字段之后,将会议主题和新人培训会议作 为摘要51的第一行,将会议时间和今天下午14:30作为摘要51的第二行,将会议地点和某某世纪城作为摘要51的第三行在对话界面中显示。用户还可以基于显示的摘要51进行回复,回复的内容可以显示在摘要51的上方52处以表示摘要51和回复内容之间的对应关系。As shown in Figure 5B, for the target reference text 50 shown in Figure 5A, when the task Task1 judges the type of the target reference text 30, the probability of classify[0] is less than the probability of classify[1], indicating that the target reference The text type of the text 30 is suitable for extracting abstracts by means of extracting key fields (the second extraction method). Therefore, after the tags and key fields are extracted according to steps S411 to S414 through task Task3, the meeting theme and newcomer training The meeting is used as the first line of summary 51, the meeting time and 14:30 this afternoon are used as the second line of summary 51, and the meeting location and XX Century City are displayed in the dialogue interface as the third line of summary 51. The user can also make a reply based on the displayed summary 51 , and the content of the reply can be displayed at 52 above the summary 51 to indicate the correspondence between the summary 51 and the content of the reply.
由此,本申请实施例的一种信息显示方法,确定用户在对话界面中引用的目标引用文本,计算目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。Thus, an information display method in an embodiment of the present application determines the target reference text quoted by the user in the dialog interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score value of at least two sentences in the target reference text. The target sentence whose score value is higher than the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
图6示出本申请实施例提供的一种信息显示方法的一种流程示意图,该方法可以由电子设备执行,例如终端设备。也就是说,上述的信息显示方法可以由安装在终端设备的软件或硬件来执行。如图6所示,该方法可以包括以下步骤。FIG. 6 shows a schematic flowchart of an information display method provided by an embodiment of the present application, and the method may be executed by an electronic device, such as a terminal device. That is to say, the above information display method can be implemented by software or hardware installed in the terminal device. As shown in Fig. 6, the method may include the following steps.
S610:确定用户在对话界面中引用的目标引用文本。S610: Determine the target reference text quoted by the user in the dialogue interface.
S611:计算目标引用文本中至少两个句子的第一得分值。S611: Calculate first score values of at least two sentences in the target reference text.
S612:选取至少两个句子中的第一得分值高于分数阈值的目标句子作为摘要。S612: Select a target sentence whose first score value is higher than a score threshold among at least two sentences as a summary.
S613:在对话界面中显示摘要。S613: Display the summary in the dialogue interface.
S610-S613与图1实施例中S110-S113具有相同或相似的实现方式,其可以互相参照,本申请实施例在此不再赘述。S610-S613 have the same or similar implementation manners as S110-S113 in the embodiment in FIG. 1 , which can be referred to each other, and will not be described again in this embodiment of the present application.
S614:选取预定时间内与目标引用文本相关联的多个待选关联文本。S614: Select a plurality of associated texts associated with the target reference text within a predetermined time period.
S615:对目标引用文本和待选关联文本进行关联性分析,得到关联度。S615: Perform correlation analysis on the target reference text and the associated text to be selected to obtain a correlation degree.
S616:对各关联度进行排名,选取排名满足要求的待选关联文本为目标关联文本。具体来说,预定时间可以为任意时间段,如6小时。S616: Rank each degree of association, and select a candidate association text whose ranking meets the requirements as a target association text. Specifically, the predetermined time may be any time period, such as 6 hours.
具体来讲,对目标引用文本和待选关联文本进行关联性分析时,可以将目标引用文本和关联文本一对一组合,然后采用Bert语言模型对目标引用文本和关联文本进行语义表示,将目标引用文本的语义表示记为H1,将关联文本的语义表示记为H2,H1和H2经Bert语言模型处理后以向量进行表示,然后采用以下的融合策略对H1和H2进行融合,具体为:Specifically, when performing correlation analysis on the target reference text and the associated text to be selected, the target reference text and the associated text can be combined one-to-one, and then the Bert language model is used to semantically represent the target reference text and the associated text, and the target The semantic representation of the quoted text is recorded as H1, and the semantic representation of the associated text is recorded as H2. H1 and H2 are expressed as vectors after being processed by the Bert language model, and then the following fusion strategy is used to fuse H1 and H2, specifically:
Figure PCTCN2022096729-appb-000001
Figure PCTCN2022096729-appb-000001
其中,
Figure PCTCN2022096729-appb-000002
表示拼接,“*”表示相乘,“-”表示相减,H1*H2表示的是各向量相乘,即H1和H2之间的字符交换,H1-H2表示的是消除H1和H2里相同的字符,Fusion表示融合后的语义表示。
in,
Figure PCTCN2022096729-appb-000002
Indicates splicing, "*" means multiplication, "-" means subtraction, H1*H2 means multiplication of vectors, that is, character exchange between H1 and H2, H1-H2 means eliminating the same in H1 and H2 characters, and Fusion represents the fused semantic representation.
将上述融合后的Fusion输入到前向神经网络计算融合后的Fusion的关联度的得分值,将各个得分值进行排名,将得分值超过阈值的待选关联文本作为目标关联文本,其中,阈值可以根据实际情况确定,本申请实施例在此并不作限定。Input the Fusion after fusion above to the forward neural network to calculate the score value of the relevance degree of Fusion after fusion, rank each score value, and use the candidate association text whose score value exceeds the threshold as the target association text, where , the threshold may be determined according to the actual situation, which is not limited in this embodiment of the present application.
S617:响应于对摘要的触发操作,将对话界面显示摘要的位置跳转至目标关联文本所在的位置。S617: In response to the trigger operation on the summary, jump from the position where the summary is displayed on the dialog interface to the position where the target associated text is located.
基于图5B所示例的场景,在按照步骤S613选取与会议通知(目标引用文本50)相关的目标关联文本为关联文本1、关联文本2和关联文本3,如图7A所示的,当用户点击或长按摘要51所在的位置,显示悬浮列表70,该悬浮列表70中,显示目标关联文本的关联标记,可以按照关联度的值大小对关联标记进行排名,将关联度最高的关联文本标记为相关性1、依次类推为相关性2和相关性3。Based on the scene illustrated in Figure 5B, the target associated texts related to the meeting notification (target reference text 50) are selected as associated text 1, associated text 2 and associated text 3 according to step S613, as shown in Figure 7A, when the user clicks Or long press the position of the abstract 51 to display the floating list 70. In the floating list 70, the associated tags of the target associated text are displayed. The associated tags can be ranked according to the value of the degree of association, and the associated text with the highest degree of association is marked as Correlation 1, and so on are correlation 2 and correlation 3.
如图7B所示的,当用户点击或长按关联标记所在的位置时,如用户点击相关性1的关联标记时,则由图7A所示的对话界面显示摘要51的位置直接跳转到相关性1所对应的关联文本71所在的位置,关联文本71所在的位置如图7C所示。As shown in Figure 7B, when the user clicks or long-presses the position where the associated mark is located, such as when the user clicks on the associated mark of Relevance 1, the dialogue interface shown in Figure 7A will directly jump to the relevant position where the summary 51 is displayed. The location of the associated text 71 corresponding to property 1 is shown in FIG. 7C .
进一步,如图8所示的,在S610至S613之后,该方法还包括:Further, as shown in FIG. 8, after S610 to S613, the method further includes:
S618:响应于对摘要的触发操作,由对话界面显示摘要的位置跳转至目标引用文本所在的位置。S618: In response to the trigger operation on the summary, jump from the position where the summary is displayed on the dialogue interface to the position where the target reference text is located.
图7A所提供的场景,当用户点击或长按摘要51所在的位置,显示悬浮列表70,该悬浮列表70中,显示目标引用文本50的原位置标记(如原位置)。In the scenario shown in FIG. 7A , when the user clicks or long-presses the location of the summary 51 , a floating list 70 is displayed, and the original location mark (such as the original location) of the target reference text 50 is displayed in the floating list 70 .
当用户点击或长按位置标记(原位置)所在的位置时,则由对话界面显示摘要51的位置直接跳转到目标引用文本50的原位置。When the user clicks or long presses the position where the position marker (original position) is located, the position of the summary 51 displayed on the dialogue interface will directly jump to the original position of the target reference text 50 .
本申请实施例的一种信息显示方法,确定用户在对话界面中引用的目标引用文本,计算目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。An information display method according to an embodiment of the present application, which determines the target reference text quoted by the user in the dialogue interface, calculates the first score value of at least two sentences in the target reference text, and selects the first score value of at least two sentences The target sentence above the score threshold is used as a summary, and the summary is displayed in the dialog interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
此外,通过选取与目标引用文本相关联的目标关联信息,响应于对摘要的触发操作,可以由对话界面显示摘要的位置直接跳转到目标关联信息的位置,为用户提供目标引用文本与上下文的关联信息,从而达到目标引用文本与下文之间关联的目的,增强用户对目标引用文本的理解,进一步提升了用户体验感。In addition, by selecting the target related information associated with the target reference text, in response to the trigger operation on the summary, the position where the summary is displayed on the dialogue interface can directly jump to the position of the target related information, providing the user with a link between the target reference text and the context. Link information, so as to achieve the purpose of linking the target reference text with the following text, enhance the user's understanding of the target reference text, and further improve the user experience.
进一步,通过响应于对摘要的触发操作,可以由对话界面显示摘要的位置直接跳转到目标引用文本的原位置,可以便于用户阅读完整的目标引用文本的内容,增强用户对目标引用文本的理解,进一步提升了用户体验感。Further, by responding to the trigger operation on the abstract, the position where the abstract is displayed on the dialogue interface can directly jump to the original position of the target reference text, which can facilitate the user to read the complete content of the target reference text and enhance the user's understanding of the target reference text , to further enhance the user experience.
需要说明的是,本申请实施例提供的信息显示方法,执行主体可以 为信息显示装置,或者该信息显示装置中的用于执行信息显示方法的控制模块。本申请实施例中以信息显示装置执行信息显示方法为例,说明本申请实施例提供的信息显示装置。It should be noted that, for the information display method provided in the embodiment of the present application, the execution subject may be an information display device, or a control module in the information display device for executing the information display method. In the embodiment of the present application, the information display device provided in the embodiment of the present application is described by taking the information display device executing the information display method as an example.
图9示出本申请实施例提供的一种信息显示装置的结构示意图,该装置900包括:确定模块910、第一计算模块920、第一选取模块930和显示模块940。FIG. 9 shows a schematic structural diagram of an information display device provided by an embodiment of the present application. The device 900 includes: a determination module 910 , a first calculation module 920 , a first selection module 930 and a display module 940 .
确定模块910用于确定用户在对话界面中引用的目标引用文本。第一计算模块920用于计算所述目标引用文本中至少两个句子的第一得分值。第一选取模块930用于选取所述至少两个句子中所述第一得分值高于分数阈值的目标句子作为摘要。显示模块940用于在所述对话界面中显示所述摘要。The determination module 910 is used to determine the target reference text quoted by the user in the dialogue interface. The first calculation module 920 is used to calculate the first score values of at least two sentences in the target reference text. The first selection module 930 is configured to select a target sentence whose first score value is higher than a score threshold among the at least two sentences as an abstract. The display module 940 is used for displaying the summary in the dialogue interface.
本申请实施例提供的一种信息显示装置,确定用户在对话界面中引用的目标引用文本,计算目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。An information display device provided by an embodiment of the present application determines the target reference text quoted by the user in the dialogue interface, calculates the first score values of at least two sentences in the target reference text, and selects the first score of at least two sentences Target sentences whose values are higher than the score threshold are used as summaries, and the summaries are displayed in the dialog interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience.
在一种可能的实现方式中,第一计算模块920包括:In a possible implementation manner, the first computing module 920 includes:
语义表示单元,用于对所述目标引用文本中的至少两个句子进行语义表示。处理单元,用于对进行语义表示后的至少两个句子进行均值化处理,得到处理后的句子。第一计算单元,用于计算所述处理后的句子的第一得分值。A semantic representation unit, configured to perform semantic representation on at least two sentences in the target reference text. The processing unit is configured to perform mean value processing on at least two sentences after performing semantic representation to obtain a processed sentence. A first calculation unit, configured to calculate the first score value of the processed sentence.
在一种可能的实现方式中,第一选取模块930包括:组合单元,用于将所述句子进行组合,得到组合句子。第二计算单元,用于根据所述第一得分值计算所述组合句子的第二得分值。选取单元,用于从多个所述组合句子中选取所述第二得分值高于分数阈值的至少一个目标组合句子作为所述目标句子,其中,所述目标句子的长度不超过所述显示长 度阈值。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。In a possible implementation manner, the first selecting module 930 includes: a combining unit, configured to combine the sentences to obtain a combined sentence. A second calculation unit, configured to calculate a second score value of the combined sentence according to the first score value. A selecting unit, configured to select at least one target combined sentence whose second score value is higher than a score threshold from a plurality of combined sentences as the target sentence, wherein the length of the target sentence does not exceed the displayed length threshold. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
在一种可能的实现方式中,该装置900还包括:第二选取模块,用于选取预定时间内与所述目标引用文本相关联的多个待选关联文本。分析模块,用于对所述目标引用文本和所述待选关联文本进行关联性分析,得到关联度。排名模块,用于对各所述关联度进行排名,选取排名满足要求的待选关联文本为目标关联文本。第一跳转模块,用于响应于对所述摘要的触发操作,由所述对话界面显示所述摘要的位置跳转至所述目标关联文本所在的位置。In a possible implementation manner, the apparatus 900 further includes: a second selecting module, configured to select a plurality of associated texts to be selected associated with the target quoted text within a predetermined time. An analysis module, configured to perform a correlation analysis on the target reference text and the associated text to be selected to obtain a degree of correlation. The ranking module is used to rank each degree of association, and select the candidate association text whose ranking meets the requirements as the target association text. The first jumping module is configured to jump from the position where the summary is displayed on the dialog interface to the position where the target associated text is located in response to a trigger operation on the summary.
在一种可能的实现方式中,该装置900还包括:第二跳转模块(图中未示出)。In a possible implementation manner, the apparatus 900 further includes: a second jump module (not shown in the figure).
第二跳转模块,用于响应于对摘要的触发操作,将对话界面显示摘要的位置跳转至目标引用文本所在的位置。The second jumping module is configured to jump from the position where the summary is displayed on the dialog interface to the position where the target reference text is located in response to a trigger operation on the summary.
本申请实施例提供的该装置900,可执行前文方法实施例中的各方法,并实现前文方法实施例中的各方法的功能和有益效果,在此不再赘述。The device 900 provided in the embodiment of the present application can execute the methods in the foregoing method embodiments, and realize the functions and beneficial effects of the methods in the foregoing method embodiments, which will not be repeated here.
本申请实施例中的信息显示装置可以是装置,也可以是终端中的部件、集成电路、或芯片。该装置可以是移动电子设备,也可以为非移动电子设备。示例性的,移动电子设备可以为手机、平板电脑、笔记本电脑、掌上电脑、车载电子设备、可穿戴设备、超级移动个人计算机(ultra-mobile personal computer,UMPC)、上网本或者个人数字助理(personal digital assistant,PDA)等,非移动电子设备可以为服务器、网络附属存储器(Network Attached Storage,NAS)、个人计算机(personal computer,PC)、电视机(television,TV)、柜员机或者自助机等,本申请实施例不作具体限定。The information display device in the embodiment of the present application may be a device, or a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant). assistant, PDA), etc., non-mobile electronic devices can be servers, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (television, TV), teller machine or self-service machine, etc., this application Examples are not specifically limited.
本申请实施例中的信息显示装置可以为具有操作系统的装置。该操 作系统可以为安卓(Android)操作系统,可以为ios操作系统,还可以为其他可能的操作系统,本申请实施例不作具体限定。The information display device in the embodiment of the present application may be a device with an operating system. The operating system may be an Android operating system, an ios operating system, or other possible operating systems, which are not specifically limited in this embodiment of the present application.
本申请实施例提供的信息显示装置能够实现图1至图8的方法实施例实现的各个过程,为避免重复,这里不再赘述。The information display device provided by the embodiment of the present application can realize various processes realized by the method embodiments in FIG. 1 to FIG. 8 , and details are not repeated here to avoid repetition.
可选地,如图10所示,本申请实施例还提供一种电子设备100,包括处理器101,存储器102,存储在存储器102上并可在处理器101上运行的程序或指令,该程序或指令被处理器101执行时实现上述信息显示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。Optionally, as shown in FIG. 10 , the embodiment of the present application also provides an electronic device 100, including a processor 101, a memory 102, and a program or instruction stored in the memory 102 and operable on the processor 101. The program Or, when the instructions are executed by the processor 101, each process of the above-mentioned information display method embodiment can be realized, and the same technical effect can be achieved. To avoid repetition, details are not repeated here.
图11为实现本申请实施例的一种电子设备的硬件结构示意图。FIG. 11 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.
该电子设备1000包括但不限于:射频单元1001、网络模块1002、音频输出单元1003、输入单元1004、传感器1005、显示单元1006、用户输入单元1007、接口单元1008、存储器1009、以及处理器1010等部件。The electronic device 1000 includes, but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010, etc. part.
本领域技术人员可以理解,电子设备1000还可以包括给各个部件供电的电源(比如电池),电源可以通过电源管理系统与处理器1010逻辑相连,从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。图11中示出的电子设备结构并不构成对电子设备的限定,电子设备可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置,在此不再赘述。Those skilled in the art can understand that the electronic device 1000 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 1010 through the power management system, so that the management of charging, discharging, and function can be realized through the power management system. Consumption management and other functions. The structure of the electronic device shown in FIG. 11 does not constitute a limitation to the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine some components, or arrange different components, and details will not be repeated here. .
用户输入单元1007,用于确定用户在对话界面中引用的目标引用文本,处理器1010,用于计算所述目标引用文本中至少两个句子的第一得分值,选取所述至少两个句子中所述第一得分值高于分数阈值的目标句子作为摘要,显示单元1006在对话界面中显示摘要。The user input unit 1007 is used to determine the target reference text quoted by the user in the dialogue interface, and the processor 1010 is used to calculate the first score value of at least two sentences in the target reference text, and select the at least two sentences The target sentence whose first score value is higher than the score threshold is used as a summary, and the display unit 1006 displays the summary in the dialogue interface.
处理器1010还用于对所述目标引用文本中的至少两个句子进行语义表示。对进行语义表示后的至少两个句子进行均值化处理,得到处理 后的句子。计算所述处理后的句子的第一得分值。The processor 1010 is further configured to semantically represent at least two sentences in the target reference text. At least two sentences after semantic representation are averaged to obtain the processed sentence. Calculating a first score value of the processed sentence.
处理器1010还用于将所述句子进行组合,得到组合句子。根据所述第一得分值计算所述组合句子的第二得分值。从多个所述组合句子中选取所述第二得分值高于分数阈值的至少一个目标组合句子作为所述目标句子,其中,所述目标句子的长度不超过所述显示长度阈值。The processor 1010 is further configured to combine the sentences to obtain a combined sentence. calculating a second score value of the combined sentence according to the first score value. Selecting at least one target combined sentence whose second score value is higher than a score threshold from a plurality of combined sentences is selected as the target sentence, wherein the length of the target sentence does not exceed the display length threshold.
处理器1010还用于选取预定时间内与所述目标引用文本相关联的多个待选关联文本。对所述目标引用文本和所述待选关联文本进行关联性分析,得到关联度。对各所述关联度进行排名,选取排名满足要求的待选关联文本为目标关联文本。响应于对所述摘要的触发操作,由所述对话界面显示所述摘要的位置跳转至所述目标关联文本所在的位置。The processor 1010 is further configured to select a plurality of candidate associated texts associated with the target referenced text within a predetermined time period. A correlation analysis is performed on the target reference text and the associated text to be selected to obtain a correlation degree. Rank each of the related degrees, and select the candidate related text whose ranking meets the requirements as the target related text. In response to a trigger operation on the summary, the dialogue interface displays a position where the summary is displayed and jumps to a position where the target associated text is located.
处理器1010还用于响应于对摘要的触发操作,将对话界面显示摘要的位置跳转至目标引用文本所在的位置。The processor 1010 is further configured to, in response to a trigger operation on the summary, jump from the position where the summary is displayed on the dialogue interface to the position where the target reference text is located.
其中,射频单元1001可用于收发信息或通话过程中,信号的接收和发送,具体的,将来自基站的下行数据接收后,给处理器1010处理;另外,将上行的数据发送给基站。通常,射频单元1001包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器、双工器等。此外,射频单元1001还可以通过无线通信系统与网络和其他设备通信。Among them, the radio frequency unit 1001 can be used for sending and receiving information or receiving and sending signals during a call. Specifically, after receiving downlink data from the base station, it is processed by the processor 1010; in addition, the uplink data is sent to the base station. Generally, the radio frequency unit 1001 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 1001 can also communicate with the network and other devices through a wireless communication system.
电子设备通过网络模块1002为用户提供了无线的宽带互联网访问,如帮助用户收发电子邮件、浏览网页和访问流式媒体等。The electronic device provides users with wireless broadband Internet access through the network module 1002, such as helping users send and receive emails, browse web pages, and access streaming media.
音频输出单元1003可以将射频单元1001或网络模块1002接收的或者在存储器1009中存储的音频数据转换成音频信号并且输出为声音。音频输出单元1003包括扬声器、蜂鸣器以及受话器等。The audio output unit 1003 may convert audio data received by the radio frequency unit 1001 or the network module 1002 or stored in the memory 1009 into an audio signal and output as sound. The audio output unit 1003 includes a speaker, a buzzer, a receiver, and the like.
应理解的是,本申请实施例中,输入单元1004可以包括图形处理器(Graphics Processing Unit,GPU)10041和麦克风10042,图形处理器10041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。It should be understood that, in the embodiment of the present application, the input unit 1004 may include a graphics processor (Graphics Processing Unit, GPU) 10041 and a microphone 10042, and the graphics processor 10041 is used for the image capture device ( Such as the image data of the still picture or video obtained by the camera) for processing.
显示单元1006可包括显示面板10061,可以采用液晶显示器、有机发光二极管等形式来配置显示面板10061。用户输入单元1007包括触控面板10071以及其他输入设备10072。触控面板10071,也称为触摸屏。触控面板10071可包括触摸检测装置和触摸控制器两个部分。其他输入设备10072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。存储器1009可用于存储软件程序以及各种数据,包括但不限于应用程序和操作系统。处理器1010可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作系统、用户界面和应用程序等,调制解调处理器主要处理无线通信。可以理解的是,上述调制解调处理器也可以不集成到处理器1010中。The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1007 includes a touch panel 10071 and other input devices 10072 . The touch panel 10071 is also called a touch screen. The touch panel 10071 may include two parts, a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, and joysticks, which will not be repeated here. The memory 1009 can be used to store software programs as well as various data, including but not limited to application programs and operating systems. Processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes operating systems, user interfaces, and application programs, and the modem processor mainly processes wireless communications. It can be understood that the foregoing modem processor may not be integrated into the processor 1010 .
电子设备1000还包括至少一种传感器1005,比如光传感器、运动传感器以及其他传感器。具体地,光传感器包括环境光传感器及接近传感器,其中,环境光传感器可根据环境光线的明暗来调节显示面板10061的亮度,接近传感器可在电子设备1000移动到耳边时,关闭显示面板10061和/或背光。The electronic device 1000 also includes at least one sensor 1005, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 10061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 10061 and the / or backlighting.
显示单元1006用于显示由用户输入的信息或提供给用户的信息(如显示摘要)。显示单元1006可包括显示面板10061,可以采用液晶显示器(Liquid Crystal Display,LCD)、有机发光二极管(Organic Light-Emitting Diode,OLED)等形式来配置显示面板10061。The display unit 1006 is used for displaying information input by the user or information provided to the user (such as displaying a summary). The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like.
用户输入单元1007可用于接收输入的数字或字符信息,以及产生与电子设备的用户设置以及功能控制有关的键信号输入。具体地,用户输入单元1007包括触控面板10071以及其他输入设备10072。触控面板10071,也称为触摸屏,可收集用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触控面板10071上或在触控面板10071附近的操作)。The user input unit 1007 can be used to receive input numbers or character information, and generate key signal input related to user settings and function control of the electronic device. Specifically, the user input unit 1007 includes a touch panel 10071 and other input devices 10072 . The touch panel 10071, also referred to as a touch screen, can collect touch operations of the user on or near it (for example, the user uses any suitable object or accessory such as a finger and a stylus on the touch panel 10071 or near the touch panel 10071 operate).
触控面板10071可包括触摸检测装置和触摸控制器两个部分。其中,触摸检测装置检测用户的触摸方位,并检测触摸操作带来的信号,将信号传送给触摸控制器;触摸控制器从触摸检测装置上接收触摸信息,并将它转换成触点坐标,再送给处理器1010,接收处理器1010发来的命令并加以执行。此外,可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板10071。除了触控面板10071,用户输入单元1007还可以包括其他输入设备10072。具体地,其他输入设备10072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。The touch panel 10071 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and sends it to the For the processor 1010, receive the command sent by the processor 1010 and execute it. In addition, the touch panel 10071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 10071 , the user input unit 1007 may also include other input devices 10072 . Specifically, other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.
进一步的,触控面板10071可覆盖在显示面板10061上,当触控面板10071检测到在其上或附近的触摸操作后,传送给处理器1010以确定触摸事件的类型,随后处理器1010根据触摸事件的类型在显示面板10061上提供相应的视觉输出。虽然在图11中,触控面板10071与显示面板10061是作为两个独立的部件来实现电子设备的输入和输出功能,但是在某些实施例中,可以将触控面板10071与显示面板10061集成而实现电子设备的输入和输出功能,具体此处不做限定。Furthermore, the touch panel 10071 can be covered on the display panel 10061, and when the touch panel 10071 detects a touch operation on or near it, it will be sent to the processor 1010 to determine the type of the touch event, and then the processor 1010 will The type of event provides a corresponding visual output on the display panel 10061. Although in FIG. 11, the touch panel 10071 and the display panel 10061 are used as two independent components to realize the input and output functions of the electronic device, in some embodiments, the touch panel 10071 and the display panel 10061 can be integrated The implementation of the input and output functions of the electronic device is not specifically limited here.
接口单元1008为外部装置与电子设备1000连接的接口。例如,外部装置可以包括有线或无线头戴式耳机端口、外部电源(或电池充电器)端口、有线或无线数据端口、存储卡端口、用于连接具有识别模块的装置的端口、音频输入/输出(I/O)端口、视频I/O端口、耳机端口等等。接口单元1008可以用于接收来自外部装置的输入(例如,数据信息、电力等等)并且将接收到的输入传输到电子设备1000内的一个或多个元件或者可以用于在电子设备1000和外部装置之间传输数据。The interface unit 1008 is an interface for connecting an external device to the electronic device 1000 . For example, an external device may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, audio input/output (I/O) ports, video I/O ports, headphone ports, and more. The interface unit 1008 can be used to receive input from an external device (for example, data information, power, etc.) transfer data between devices.
存储器1009可用于存储软件程序以及各种数据。存储器1009可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等) 等;存储数据区可存储根据手机的使用所创建的数据(比如音频数据、电话本等)等。此外,存储器1009可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。The memory 1009 can be used to store software programs as well as various data. The memory 1009 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.); Data created by the use of mobile phones (such as audio data, phonebook, etc.), etc. In addition, the memory 1009 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.
处理器1010是电子设备的控制中心,利用各种接口和线路连接整个电子设备的各个部分,通过运行或执行存储在存储器1009内的软件程序和/或模块,以及调用存储在存储器1009内的数据,执行电子设备的各种功能和处理数据,从而对电子设备进行整体监控。处理器1010可包括一个或多个处理单元;优选的,处理器1010可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作系统、用户界面和应用程序等,调制解调处理器主要处理无线通信。可以理解的是,上述调制解调处理器也可以不集成到处理器1010中。The processor 1010 is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device, by running or executing software programs and/or modules stored in the memory 1009, and calling data stored in the memory 1009 , to perform various functions of the electronic equipment and process data, so as to monitor the electronic equipment as a whole. The processor 1010 may include one or more processing units; preferably, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem The processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 1010 .
本申请实施例的一种电子设备,确定用户在对话界面中引用的目标引用文本,计算目标引用文本中至少两个句子的第一得分值,选取至少两个句子中第一得分值高于分数阈值的目标句子作为摘要,在对话界面中显示摘要。因此,本申请实施例从目标引用文本中提取摘要并显示在对话界面中,用户能够直观的了解目标引用文本的主要内容,提高了用户体验感。此外,通过计算目标引用文本中句子的第一得分值,且只将第一得分值高于分数阈值的目标句子作为摘要,采用本申请实施例提供的该种摘要提取方式,提取的摘要更准确,与目标引用文本的主旨更切合。An electronic device according to an embodiment of the present application, which determines the target reference text quoted by the user in the dialogue interface, calculates the first score value of at least two sentences in the target reference text, and selects the first score value of the at least two sentences with the highest value The target sentence above the score threshold is used as a summary, and the summary is displayed in the dialogue interface. Therefore, the embodiment of the present application extracts the abstract from the target reference text and displays it in the dialogue interface, so that the user can intuitively understand the main content of the target reference text, which improves the user experience. In addition, by calculating the first score value of the sentence in the target reference text, and only using the target sentence whose first score value is higher than the score threshold as the abstract, using the abstract extraction method provided by the embodiment of the present application, the extracted abstract More accurate and more relevant to the gist of the target cited text.
本申请实施例还提供一种可读存储介质,可读存储介质上存储有程序或指令,该程序或指令被处理器执行时实现上述信息显示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, each process of the above-mentioned information display method embodiment is realized, and the same technology can be achieved. Effect, in order to avoid repetition, will not repeat them here.
其中,处理器为上述实施例中的电子设备中的处理器。可读存储介质,包括计算机可读存储介质,如计算机只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者 光盘等。Wherein, the processor is the processor in the electronic device in the foregoing embodiments. Readable storage media include computer readable storage media, such as computer read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, etc.
本申请实施例另提供了一种芯片,芯片包括处理器和通信接口,通信接口和处理器耦合,处理器用于运行程序或指令,实现上述信息显示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。The embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, the processor is used to run programs or instructions, and realize the various processes of the above information display method embodiments, and can achieve the same Technical effects, in order to avoid repetition, will not be repeated here.
应理解,本申请实施例提到的芯片还可以称为系统级芯片、系统芯片、芯片系统或片上系统芯片等。It should be understood that the chips mentioned in the embodiments of the present application may also be called system-on-chip, system-on-chip, system-on-a-chip, or system-on-a-chip.
本申请实施例另提供了一种计算机程序产品,所述计算机程序产品被至少一个处理器执行以实现上述信息显示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。The embodiment of the present application further provides a computer program product, the computer program product is executed by at least one processor to implement the various processes of the above information display method embodiment, and can achieve the same technical effect, in order to avoid repetition, it is not repeated here Let me repeat.
本申请实施例另提供了一种电子设备,电子设备被配置成用于执行上述信息显示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。The embodiment of the present application further provides an electronic device, which is configured to execute the processes of the foregoing information display method embodiments, and can achieve the same technical effect. To avoid repetition, details are not repeated here.
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外,需要指出的是,本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能,还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能,例如,可以按不同于所描述的次序来执行所描述的方法,并且还可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然 也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,或者网络设备等)执行本申请各个实施例的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present application can be embodied in the form of computer software products, which are stored in a storage medium (such as ROM/RAM, magnetic disk, etc.) , optical disc), including several instructions to enable a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present application.
上面结合附图对本申请的实施例进行了描述,但是本申请并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本申请的启示下,在不脱离本申请宗旨和权利要求所保护的范围情况下,还可做出很多形式,均属于本申请的保护之内。The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementations. The above-mentioned specific implementations are only illustrative and not restrictive. Those of ordinary skill in the art will Under the inspiration of this application, without departing from the purpose of this application and the scope of protection of the claims, many forms can also be made, all of which belong to the protection of this application.

Claims (15)

  1. 一种信息显示方法,其中,所述方法包括:An information display method, wherein the method includes:
    确定用户在对话界面中引用的目标引用文本;Determining the target citation text that the user cites in the conversational interface;
    计算所述目标引用文本中至少两个句子的第一得分值;calculating first score values of at least two sentences in the target reference text;
    选取所述至少两个句子中所述第一得分值高于分数阈值的目标句子作为摘要;Selecting the target sentence whose first score value is higher than the score threshold in the at least two sentences as a summary;
    在所述对话界面中显示所述摘要。displaying the summary in the dialogue interface.
  2. 根据权利要求1所述的信息显示方法,其中,所述计算所述目标引用文本中至少两个句子的第一得分值包括:The information display method according to claim 1, wherein said calculating the first score values of at least two sentences in said target reference text comprises:
    对所述目标引用文本中的至少两个句子进行语义表示;Semantic representation of at least two sentences in the target reference text;
    对进行语义表示后的至少两个句子进行均值化处理,得到处理后的句子;Perform mean value processing on at least two sentences after performing semantic representation to obtain a processed sentence;
    计算所述处理后的句子的第一得分值。Calculating a first score value of the processed sentence.
  3. 根据权利要求1所述的信息显示方法,其中,所述选取所述至少两个句子中所述第一得分值高于分数阈值的目标句子作为摘要包括:The information display method according to claim 1, wherein said selecting a target sentence whose first score value is higher than a score threshold in said at least two sentences as an abstract comprises:
    将所述句子进行组合,得到组合句子;Combining the sentences to obtain a combined sentence;
    根据所述第一得分值计算所述组合句子的第二得分值;calculating a second score value of the combined sentence according to the first score value;
    从多个所述组合句子中选取所述第二得分值高于分数阈值的至少一个目标组合句子作为所述目标句子,其中,所述目标句子的长度不超过显示长度阈值。Selecting at least one target combined sentence whose second score value is higher than a score threshold from a plurality of combined sentences is selected as the target sentence, wherein the length of the target sentence does not exceed a display length threshold.
  4. 根据权利要求1所述的信息显示方法,其中,在所述对话界面中显示所述摘要之后,所述方法还包括:The information display method according to claim 1, wherein after displaying the summary in the dialogue interface, the method further comprises:
    选取预定时间内与所述目标引用文本相关联的多个待选关联文本;Selecting a plurality of associated texts to be selected associated with the target referenced text within a predetermined time;
    对所述目标引用文本和所述待选关联文本进行关联性分析,得到关联度;Performing a correlation analysis on the target reference text and the associated text to be selected to obtain a degree of correlation;
    对各所述关联度进行排名,选取排名满足要求的待选关联文本为目标关联文本;Ranking each degree of association, selecting the associated text to be selected whose ranking meets the requirements as the target associated text;
    响应于对所述摘要的触发操作,由所述对话界面显示所述摘要的位置跳转至所述目标关联文本所在的位置。In response to a trigger operation on the summary, the dialogue interface displays a position where the summary is displayed and jumps to a position where the target associated text is located.
  5. 根据权利要求1所述的信息显示方法,其中,在所述对话界面中显示所述摘要之后,所述方法还包括:The information display method according to claim 1, wherein after displaying the summary in the dialogue interface, the method further comprises:
    响应于对所述摘要的触发操作,由所述对话界面显示所述摘要的位置跳转至所述目标引用文本所在的位置。In response to a trigger operation on the abstract, the dialog interface displays the location of the abstract and jumps to the location of the target reference text.
  6. 一种信息显示装置,其中,所述装置包括:An information display device, wherein the device includes:
    确定模块,用于确定用户在对话界面中引用的目标引用文本;A determination module, configured to determine the target reference text quoted by the user in the dialogue interface;
    第一计算模块,用于计算所述目标引用文本中至少两个句子的第一得分值;A first calculation module, configured to calculate a first score value of at least two sentences in the target reference text;
    第一选取模块,用于选取所述至少两个句子中所述第一得分值高于分数阈值的目标句子作为摘要;The first selection module is used to select the target sentence whose first score value is higher than the score threshold in the at least two sentences as the abstract;
    显示模块,用于在所述对话界面中显示所述摘要。A display module, configured to display the summary in the dialogue interface.
  7. 根据权利要求6所述的信息显示装置,其中,所述第一计算模块包括:The information display device according to claim 6, wherein the first calculating module comprises:
    语义表示单元,用于对所述目标引用文本中的至少两个句子进行语义表示;a semantic representation unit, configured to semantically represent at least two sentences in the target reference text;
    处理单元,用于对进行语义表示后的至少两个句子进行均值化处理,得到处理后的句子;A processing unit, configured to perform mean value processing on at least two sentences after performing semantic representation, to obtain a processed sentence;
    第一计算单元,用于计算所述处理后的句子的第一得分值。A first calculation unit, configured to calculate the first score value of the processed sentence.
  8. 根据权利要求6所述的信息显示装置,其中,所述第一选取模块包括:The information display device according to claim 6, wherein the first selection module comprises:
    组合单元,用于将所述句子进行组合,得到组合句子;A combining unit is used to combine the sentences to obtain a combined sentence;
    第二计算单元,用于根据所述第一得分值计算所述组合句子的第二得分值;a second calculation unit, configured to calculate a second score value of the combined sentence according to the first score value;
    选取单元,用于从多个所述组合句子中选取所述第二得分值高于分数阈值的至少一个目标组合句子作为所述目标句子,其中,所述目标句子的长度不超过所述显示长度阈值。A selecting unit, configured to select at least one target combined sentence whose second score value is higher than a score threshold from a plurality of combined sentences as the target sentence, wherein the length of the target sentence does not exceed the displayed length threshold.
  9. 根据权利要求6所述的信息显示装置,其中,所述装置还包括:The information display device according to claim 6, wherein the device further comprises:
    第二选取模块,用于选取预定时间内与所述目标引用文本相关联的多个待选关联文本;The second selection module is used to select a plurality of associated texts to be selected associated with the target reference text within a predetermined time;
    分析模块,用于对所述目标引用文本和所述待选关联文本进行关联性分析,得到关联度;An analysis module, configured to perform a correlation analysis on the target reference text and the associated text to be selected to obtain a degree of correlation;
    排名模块,用于对各所述关联度进行排名,选取排名满足要求的待选关联文本为目标关联文本;A ranking module, configured to rank each degree of association, and select a candidate association text whose ranking meets the requirements as the target association text;
    第一跳转模块,用于响应于对所述摘要的触发操作,由所述对话界面显示所述摘要的位置跳转至所述目标关联文本所在的位置。The first jumping module is configured to jump from the position where the summary is displayed on the dialog interface to the position where the target associated text is located in response to a trigger operation on the summary.
  10. 根据权利要求6所述的信息显示装置,其中,所述装置还包括:The information display device according to claim 6, wherein the device further comprises:
    第二跳转模块,用于响应于对所述摘要的触发操作,由所述对话界面显示所述摘要的位置跳转至所述目标引用文本所在的位置。The second jumping module is configured to jump from the position where the summary is displayed on the dialogue interface to the position where the target reference text is located in response to a trigger operation on the summary.
  11. 一种电子设备,其中,包括处理器,存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1-5任意一项所述的信息显示方法的步骤。An electronic device, including a processor, a memory, and a program or instruction stored in the memory and operable on the processor, when the program or instruction is executed by the processor, the invention according to claim 1 is realized - the steps of the information display method described in any one of 5.
  12. 一种可读存储介质,其中,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如权利要求1-5任意一项所述的信息显示方法的步骤。A readable storage medium, wherein a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the information display method according to any one of claims 1-5 are realized.
  13. 一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,其中,所述处理器用于运行程序或指令,实现如权利要求1至5中任一项所述的信息显示方法。A kind of chip, described chip comprises processor and communication interface, and described communication interface is coupled with described processor, and wherein, described processor is used for running program or order, realizes any one of claim 1 to 5 information display method.
  14. 一种计算机程序产品,其中,所述计算机程序产品被至少一个处理器执行以实现如权利要求1至5中任一项所述的信息显示方法。A computer program product, wherein the computer program product is executed by at least one processor to implement the information display method according to any one of claims 1 to 5.
  15. 一种电子设备,所述电子设备被配置成用于执行如权利要求1至5中任一项所述的信息显示方法。An electronic device configured to execute the information display method according to any one of claims 1 to 5.
PCT/CN2022/096729 2021-06-07 2022-06-02 Information display method and apparatus, electronic device, and readable storage medium WO2022257840A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110631105.7 2021-06-07
CN202110631105.7A CN113407710A (en) 2021-06-07 2021-06-07 Information display method and device, electronic equipment and readable storage medium

Publications (1)

Publication Number Publication Date
WO2022257840A1 true WO2022257840A1 (en) 2022-12-15

Family

ID=77676694

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/096729 WO2022257840A1 (en) 2021-06-07 2022-06-02 Information display method and apparatus, electronic device, and readable storage medium

Country Status (2)

Country Link
CN (1) CN113407710A (en)
WO (1) WO2022257840A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113407710A (en) * 2021-06-07 2021-09-17 维沃移动通信有限公司 Information display method and device, electronic equipment and readable storage medium
CN114546192B (en) * 2021-12-31 2023-11-28 北京达佳互联信息技术有限公司 Content display processing method and device and content display method and device
CN115022272B (en) * 2022-04-02 2023-11-21 北京字跳网络技术有限公司 Information processing method, apparatus, electronic device and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109324861A (en) * 2018-09-27 2019-02-12 北京三快在线科技有限公司 Message display processing method, device, medium and electronic equipment
CN109361592A (en) * 2018-08-08 2019-02-19 腾讯科技(深圳)有限公司 A kind of instant communication message processing method, device, equipment and storage medium
CN111241267A (en) * 2020-01-10 2020-06-05 科大讯飞股份有限公司 Abstract extraction and abstract extraction model training method, related device and storage medium
US20210117617A1 (en) * 2019-10-17 2021-04-22 Amadeus S.A.S. Methods and systems for summarization of multiple documents using a machine learning approach
CN113407710A (en) * 2021-06-07 2021-09-17 维沃移动通信有限公司 Information display method and device, electronic equipment and readable storage medium

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1996959A (en) * 2005-12-31 2007-07-11 腾讯科技(深圳)有限公司 Instant communication terminal and message reference method for instant communication
CN108228541B (en) * 2016-12-22 2021-08-03 深圳市北科瑞声科技股份有限公司 Method and device for generating document abstract
CN107562732B (en) * 2017-10-26 2022-06-14 北京康夫子健康技术有限公司 Method and system for processing electronic medical record
CN109960790B (en) * 2017-12-25 2023-05-23 北京国双科技有限公司 Abstract generation method and device
CN109101489B (en) * 2018-07-18 2022-05-20 武汉数博科技有限责任公司 Text automatic summarization method and device and electronic equipment
CN109635103B (en) * 2018-12-17 2022-05-20 北京百度网讯科技有限公司 Abstract generation method and device
CN112732898A (en) * 2020-12-30 2021-04-30 平安科技(深圳)有限公司 Document abstract generation method and device, computer equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109361592A (en) * 2018-08-08 2019-02-19 腾讯科技(深圳)有限公司 A kind of instant communication message processing method, device, equipment and storage medium
CN109324861A (en) * 2018-09-27 2019-02-12 北京三快在线科技有限公司 Message display processing method, device, medium and electronic equipment
US20210117617A1 (en) * 2019-10-17 2021-04-22 Amadeus S.A.S. Methods and systems for summarization of multiple documents using a machine learning approach
CN111241267A (en) * 2020-01-10 2020-06-05 科大讯飞股份有限公司 Abstract extraction and abstract extraction model training method, related device and storage medium
CN113407710A (en) * 2021-06-07 2021-09-17 维沃移动通信有限公司 Information display method and device, electronic equipment and readable storage medium

Also Published As

Publication number Publication date
CN113407710A (en) 2021-09-17

Similar Documents

Publication Publication Date Title
WO2022078102A1 (en) Entity identification method and apparatus, device and storage medium
WO2022257840A1 (en) Information display method and apparatus, electronic device, and readable storage medium
CN107943860B (en) Model training method, text intention recognition method and text intention recognition device
CN110598046B (en) Artificial intelligence-based identification method and related device for title party
US20210182504A1 (en) Text translation method and apparatus, and storage medium
CN111177371B (en) Classification method and related device
CN110209784B (en) Message interaction method, computer device and storage medium
CN111597804B (en) Method and related device for training entity recognition model
CN111368525A (en) Information searching method, device, equipment and storage medium
CN109165292A (en) Data processing method, device and mobile terminal
CN110069769B (en) Application label generation method and device and storage device
CN111312233A (en) Voice data identification method, device and system
CN112749252A (en) Text matching method based on artificial intelligence and related device
CN114328852A (en) Text processing method, related device and equipment
EP3105858B1 (en) Electronic device and method for extracting and using sematic entity in text message of electronic device
CN116955610A (en) Text data processing method and device and storage medium
CN113157966B (en) Display method and device and electronic equipment
CN112307198B (en) Method and related device for determining abstract of single text
CN115168568A (en) Data content identification method and device and storage medium
CN113821609A (en) Answer text acquisition method and device, computer equipment and storage medium
CN112242140A (en) Intelligent device control method and device, electronic device and storage medium
KR20180033777A (en) Method, apparatus and computer program for providing image with translation
CN113569043A (en) Text category determination method and related device
CN112036135A (en) Text processing method and related device
CN111353422A (en) Information extraction method and device and electronic equipment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22819438

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE