Method and device for generating backlog, and electronic equipment

Abstract

The embodiment of the invention provides a to-do list generation method and device and electronic equipment. The to-do list generation method comprises the steps that target character information is acquired, and the target character information is character information obtained when to-be-processed voice information is converted into a character type from a voice type and is expressed through a first language type; the to-be-processed voice information comprises first voice information and second voice information, the first voice information is voice information of a second language type, the second voice information is voice information of a third language type, and the second language type is different from the third language type; determining a keyword of a first language type according to the target text information; and generating a target to-do list of the target language type based on the keyword of the first language type. A user can obtain the understandable target to-do list of the target language type according to the to-be-processed voice information without translating and summarizing the to-be-processed voice information by himself / herself.

Description

Technical Field

[0001] This application relates to the technical field of language conversion, and specifically relates to a method, apparatus, and electronic device for generating to-do items. Background Art

[0002] With the development of communication technologies, due to the efficient nature of voice communication, more and more users currently choose to use voice messages for communication.

[0003] However, when a user needs to summarize to-do items from a voice message of multiple language types, and at least one of the multiple language types is a language type that the user does not understand, it is necessary to convert the voice message into text information first, then translate the text information into text information that the user can recognize, and then the user needs to understand the text information by themselves and summarize the to-do items from it. This requires a lot of time from the user and reduces the user experience of voice message communication. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, and electronic device for generating to-do items, which helps to solve the problem that when the voice message is a voice message of multiple different language types and at least one of the multiple language types is a language type that the user does not understand, it takes a long time for the user to translate the voice message and summarize the to-do items.

[0005] In a first aspect, an embodiment of this application provides a method for generating to-do items based on voice, including the following steps:

[0006] Obtain target text information, where the target text information is the text information obtained when the voice information to be processed is converted from the voice type to the text type and is expressed in a first language type; the voice information to be processed includes first voice information and second voice information, the first voice information is voice information of a second language type, the second voice information is voice information of a third language type, and the second language type is different from the third language type;

[0007] Determine keywords of the first language type according to the target text information; the keywords include target keywords, and the target keywords are used to represent information about to-do items;

[0008] Generate a target to-do item of the target language type based on the keywords of the first language type.

[0009] In a possible implementation, obtaining the target text information includes:

[0010] Obtain the voice information to be processed;

[0011] Convert the voice information to be processed into text information of the target language type to obtain first target text information.

[0012] In a possible implementation, obtaining the target text information includes:

[0013] Receiving second target text information sent by other devices.

[0014] In a possible implementation, generating a to-do item of the target language type based on keywords of the first language type includes:

[0015] When the first language type is the same as the target language type, generating a to-do item of the target language type based on keywords of the first language type.

[0016] In a possible implementation, generating a to-do item of the target language type based on keywords of the first language type includes:

[0017] When the first language type is different from the target language type, converting keywords of the first language type into keywords of the target language type, and generating a target to-do item of the target language type based on the keywords of the target language type.

[0018] In a possible implementation, when the obtained target text information includes first target text information and second target text information, determining keywords of the first language type according to the target text information includes:

[0019] Determining first keywords of the target voice type according to the first target text information;

[0020] Determining second keywords of the first voice type according to the second target text information;

[0021] Generating a target to-do item of the target language type based on keywords of the first language type includes:

[0022] Generating a first to-do item of the target language type based on the first keywords of the target voice type;

[0023] Generating a second to-do item of the target language type based on the second keywords of the first voice type;

[0024] When the first to-do item is the same as the second to-do item, using the first to-do item of the target language type as the target to-do item.

[0025] In a possible implementation, it further includes:

[0026] When the first to-do item is different from the second to-do item, feeding back the first to-do item and the second to-do item to the user.

[0027] In a possible implementation, generating a target to-do item of the target language type based on keywords of the first language type includes:

[0028] When there are at least two target keywords in the keywords of the first language type, if at least two target keywords meet the preset conflict rules, then determine the target keyword that appears last in the target text information among the at least two target keywords, and generate a target to-do item based on the target keyword that appears last in the target text information; the preset conflict rules are pre-set rules for determining whether there is a conflict between at least two keywords.

[0029] In a possible implementation manner, generating a target to-do item of the target language type based on the keywords of the first language type includes:

[0030] When there are at least two target keywords in the keywords of the first language type, if at least two target keywords do not meet the preset conflict rules, then generate a target to-do item of the target language type based on the at least two keywords of the first language type.

[0031] In a possible implementation manner, the preset conflict rules include: at least one of a keyword with a preset negative word and information of the to-do items represented by at least two target keywords having partial repetition.

[0032] In a second aspect, an embodiment of the present application provides a device for generating a to-do item reminder based on voice, including:

[0033] An acquisition unit, configured to acquire target text information, where the target text information is the text information obtained when the to-be-processed voice information is converted from the voice type to the text type and is expressed in the first language type; the to-be-processed voice information includes first voice information and second voice information, the first voice information is voice information of the second language type, the second voice information is voice information of the third language type, and the second language type is different from the third language type;

[0034] A processing unit, configured to determine keywords of the first language type according to the target text information; the keywords include target keywords, and the target keywords are used to represent information of to-do items; generate a target to-do item of the target language type based on the keywords of the first language type.

[0035] In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory for storing computer program instructions and a processor for executing the program instructions. When the computer program instructions are executed by the processor, the electronic device is triggered to execute the method provided in the first aspect of the embodiment of the present application.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes a stored program. When the program runs, it controls the device where the computer-readable storage medium is located to execute the method provided in the first aspect of the embodiment of the present application.

[0037] Adopt the solution provided by the embodiment of the present application, extract keywords of the first language type according to the text information of the first language type converted from the voice information to be processed, and generate a target to-do item of the target language type according to the keywords of the first language type. In this way, when the voice information to be processed is voice information of multiple language types, the user can obtain a target to-do item of the target language type that can be understood according to the voice information to be processed without having to translate and summarize the voice information to be processed by himself. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0039] Figure 1 It is a flowchart of a method for generating a to-do item provided by an embodiment of the present application;

[0040] Figure 2 It is a flowchart of a method for obtaining target text information provided by an embodiment of the present application;

[0041] Figure 3 It is a schematic diagram of a meeting interface provided by an embodiment of the present application;

[0042] Figure 4 It is a schematic diagram of a device for generating a to-do item provided by an embodiment of the present application;

[0043] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed Embodiments

[0044] In order to better understand the technical solutions of the present application, the embodiments of the present application will be described in detail below with reference to the drawings.

[0045] It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0046] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "a", "the" and "said" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0047] It should be understood that the term "and / or" used herein is merely a correlative relationship describing associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the character " / " in this text generally represents an "or" relationship between the associated objects before and after.

[0048] Before specifically introducing the embodiments of the present application, first, the terms applied or possibly applied in the embodiments of the present application are explained.

[0049] In the related art, when a user needs to summarize to-do items from a piece of voice information of multiple language types, and at least one of the multiple language types is a language type that the user cannot understand, at this time, it is necessary to convert the voice information into text information, then translate the text information into text information that the user can recognize, and then the user needs to understand the text information by himself / herself and summarize the to-do items from it. In this way, it takes up a lot of the user's time and reduces the user's experience of voice information communication.

[0050] In view of the above problems, the embodiments of the present application provide a method, device, and electronic device for generating to-do items, which are beneficial to solving the problems in the related art that it takes a long time for the user to summarize to-do items from voice information of multiple language types and reduces the user's experience of language information communication. The following is a detailed description.

[0051] See Figure 1 , which is a flowchart of a method for generating to-do items provided by the embodiments of the present application. As Figure 1 shown, it includes the following steps:

[0052] Step S101: Obtain target text information.

[0053] Among them, the target text information is the text information obtained when the voice information to be processed is converted from the voice type to the text type, and is expressed in the first language type; the voice information to be processed includes the first voice information and the second voice information. The first voice information is the voice information of the second language type, and the second voice information is the voice information of the third language type, and the second language type is different from the third language type.

[0054] In the embodiments of the present application, when generating to-do items, it is necessary to extract keywords based on the text information. And since the voice information to be processed includes voice information of multiple different language types, in order to facilitate the device to extract keywords from the text information, it is necessary to first convert the voice information of multiple different types into target text information of the same type, that is, convert the voice information of the second language type and the voice information of the third language type into target text information of the first language type.

[0055] It should be noted that the first language type can be the same as one of the second language type or the third language type, or the first language type can be different from both the second language type and the third language type.

[0056] As a possible implementation, such as Figure 2 shown, obtaining the target text information includes:

[0057] S121: Obtain the voice information to be processed;

[0058] S122: Convert the voice information to be processed into text information of the target language type to obtain the first target text information.

[0059] It should be noted that the target language type is usually the language type that the device user can recognize. For example, the target language type is the language type of the device user's mother tongue. The first language type is usually the language type preset by the device. To improve the efficiency of converting voice information into text information of the target language type and thus improve the generation efficiency of to-do items, the target language type can be the same as the first language type. However, if the device has a higher recognition degree for text information of non-target language types, then to improve the accuracy of generating to-do events, the first language type and the target language type can be different. For example, the language type that the device user can recognize is Chinese, but the device has a higher recognition degree for French. Therefore, the first language type can be French and the target language type can be Chinese.

[0060] In some embodiments, converting the voice information to be processed into text information of the target language type to obtain the first target text information includes: converting the first voice information into text information of the second language type, converting the second voice information into text information of the third language type, and translating the text information of the second language type and the text information of the third language type into text information of the first language type. When the first language type is the same as the target language type, the text information of the first language type is the first target text information; when the first language type is different from the target language type, the text information of the first language type is translated into the first target text information.

[0061] In the embodiments of the present application, the voice information to be processed is converted into text information of the target language type, and the target language type is the language type that the user can understand. In this way, the to-do items generated according to the text information of the target language type can be recognized by the user, and there is no need to generate to-do items according to other language types, which improves the generation efficiency of to-do items.

[0062] In some embodiments, the to-do items in the embodiments of the present application can be generated based on the conference voice information, and the first target text information is generated during the conference. For example, such as Figure 3As shown, during the meeting, the user's meeting interface generates text information in the language type corresponding to the speech of different participants, translates the text information in other language types into the text information in the target language type, and outputs the text information in the target language type, which is the first target text information.

[0063] In the embodiments of the present application, in addition to the above-mentioned method of obtaining the target text information, as a possible implementation manner, obtaining the target text information includes:

[0064] Receiving the second target text information sent by other devices.

[0065] That is, if other devices receive the voice information to be processed and convert the voice information into text, then in order to improve the reception efficiency of the target text information, the target text information that has been converted by other devices can be directly received, that is, the second target text information is received.

[0066] It should be noted that since the second target text information is the text information in the first language type, the meaning of the first language type at this time is the language type preset by other devices. For example, the first language type is the language type that the device user in other devices can recognize.

[0067] In the embodiments of the present application, when other devices have generated the second target text information from the voice information, directly receiving the second target text information sent by other devices can eliminate the need for this device to convert the voice information into text information by itself, thereby reducing the computing amount of this device and further improving the generation efficiency of to-do items.

[0068] It should be noted that when the to-do items in the application embodiments are generated based on the meeting voice information, each participant can convert the text information in other language types into the text information in the first language type, that is, the second target text information, and send the second target text information to other participants. That is, during the meeting, some participants communicate using voice information in the second language type, and some participants communicate using voice information in the third language type. For each participant, when processing the voice information into text information, the voice information is respectively generated into text information in the first language type (the first language type can be different for each participant), where the first language type can be the language type preset by the devices of other participants. For example, as Figure 3 shown, the first language type of participant 1 is English. Therefore, when participant 1 converts the voice information in other language types into English text information, that is, the second target text information, participant 1 can send the second target text information in English type to other participants. In this way, the user as a participant receives the second target text information sent by the device of participant 1.

[0069] In some embodiments, when the to-do item in the application embodiment is generated based on the conference voice information, the first language type can also be the language type preset for the devices of the non-attendees who receive the conference voice.

[0070] In some embodiments, obtaining the target text information may include first target text information and second target text information.

[0071] Step S102: Determine the keywords of the first language type according to the target text information; the keywords include target keywords, and the target keywords are used to characterize the information of the to-do item.

[0072] In the embodiments of the present application, the keywords of the first language type are determined, and the keywords include target keywords. In this way, the keywords related to the to-do item can be determined from a large amount of target text information, which is convenient for generating a relatively concise and key-point-containing to-do item according to the keywords later, so that the user does not need to read and understand a large amount of target text information by himself.

[0073] In some embodiments, determining the keywords of the first language type according to the target text information includes: inputting the target text information into a pre-trained language recognition model, and the language recognition model outputs the keywords of the first language type.

[0074] In some embodiments, the target keywords include time, place, person, event, person's emotion, etc. For example, the target text information is to go to place a for matter yy on xx month xx day, and the participants are R and Z, and both R and Z express approval. Then the corresponding target keywords are: xx month xx day, place a, R and Z, matter yy, approval.

[0075] In some embodiments, the language recognition model can be a BERT sentiment analysis language model, so that when the target keywords include the person's emotion, the language recognition model can output relatively accurate target keywords regarding the person's emotion.

[0076] It should be noted that the above only provides several ways to determine the keywords and the specific content of the keywords, which is not an exhaustive list. In fact, any way that can extract keywords is allowed in the embodiments of the present application, and any keyword that can characterize the information of the to-do item is allowed in the embodiments of the present application.

[0077] As a possible implementation, when the obtained target text information includes first target text information and second target text information, determining the keywords of the first language type according to the target text information includes:

[0078] Determine the first keywords of the target voice type according to the first target text information;

[0079] Determine the second keywords of the first voice type according to the second target text information.

[0080] That is, since keyword extraction is applicable to both the first target text information and the second target text information, the first keyword of the target language type and the second keyword of the first language type can be determined respectively.

[0081] In some embodiments, determining the first keyword of the target language type according to the first target text information; determining the second keyword of the first language type according to the second target text information includes: inputting the first target text information into a pre-trained first language recognition model, and the first language recognition model outputs the first keyword of the target language type; inputting the second target text information into a pre-trained second language recognition model, and the second language recognition model outputs the second keyword of the first language type. Wherein, the first language recognition model and the second language recognition model are trained using corpora of different language types, that is, the first language recognition model is trained using a corpus of the target language type; the second language recognition model is trained using a corpus of the first language type.

[0082] Step S103: Generate a target to-do item of the target language type based on the keyword of the first language type.

[0083] That is, regardless of whether the first language type is the target language type, a target to-do item of the target language type is generated based on the keyword of the first language type, so that the user can understand the meaning of the target to-do item.

[0084] As a possible implementation, generating a to-do item of the target language type based on the keyword of the first language type includes:

[0085] When the first language type is the same as the target language type, generate a to-do item of the target language type based on the keyword of the first language type.

[0086] That is, when the first language type is the same as the target language type, at this time, the keyword of the first language type is the keyword of the target language type, so a to-do item of the target language type can be directly generated based on the keyword of the first language type.

[0087] In some embodiments, when the first language type is the same as the target language type, generating a to-do item of the target language type based on the keyword of the first language type includes: adding prepositions between the keywords of the first language type to generate a sentence, obtaining the to-do item of the target language type.

[0088] It should be noted that the above only provides a way to generate a to-do item of the target language type based on the keyword of the first language type, and is not an exhaustive list. In fact, any way that can generate a to-do item of the target language type based on the keyword of the first language type is allowed in the embodiments of the present application.

[0089] As a possible implementation, generating a to-do item of the target language type based on keywords of the first language type includes:

[0090] When the first language type is different from the target language type, convert the keywords of the first language type into keywords of the target language type, and generate a target to-do item of the target language type based on the keywords of the target language type.

[0091] That is, when the first language type is different from the target language type, obviously the keywords of the first language type are not the keywords of the target language type. At this time, it is necessary to convert the keywords of the first language type into keywords of the target language type, so as to generate a target to-do item of the target language type based on the keywords of the target language type.

[0092] In some embodiments, converting keywords of the first language type into keywords of the target language type includes: translating the keywords of the first language type into keywords of the target language type. The method of generating a target to-do item of the target language type based on the keywords of the target language type can refer to the method of generating a to-do item of the target language type based on the keywords of the first language type above, and will not be elaborated here.

[0093] In some embodiments, when determining a first keyword of the target voice type according to the first target text information; and determining a second keyword of the first voice type according to the second target text information, generating a target to-do item of the target language type based on the keywords of the first language type includes:

[0094] Generating a first to-do item of the target language type based on the first keyword of the target voice type;

[0095] Generating a second to-do item of the target language type based on the second keyword of the first voice type;

[0096] When the first to-do item is the same as the second to-do item, use the first to-do item of the target language type as the target to-do item.

[0097] That is, when the first to-do item is the same as the second to-do item, that is, the first to-do item and the second to-do item corroborate each other, indicating that the device's extraction of keywords and generation of to-do items are relatively accurate. At this time, using the first to-do item of the target language type as the target to-do item has a relatively low probability of omitting, adding, or incorrectly recording to-do items in the voice information.

[0098] In some embodiments, generating a second to-do item in the target language type based on the second keyword of the first voice type includes: translating the second keyword of the first voice type into the second keyword of the target language type, and generating the second to-do item in the target language type based on the second keyword of the target language type.

[0099] As a possible implementation, it further includes: when the first to-do item is different from the second to-do item, feeding back the first to-do item and the second to-do item to the user.

[0100] That is, when the first to-do item is different from the second to-do item, it means that at least one of the first to-do item and the second to-do item does not accurately express the to-do item expressed in the voice information, or there are errors, or there are omissions, or there are additions. At this time, a target to-do item cannot be generated, and the first to-do item and the second to-do item should be fed back to the user for processing to avoid generating incorrect to-do items or omitting or adding to-do items, which may delay the user's matters.

[0101] In some embodiments, feeding back the first to-do item and the second to-do item to the user includes: generating a to-be-determined interface according to the first to-do item and the second to-do item, and the to-be-determined interface includes a first to-do item entry and a second to-do item entry. The method further includes: in response to a trigger instruction for the first to-do item entry or the second to-do item entry, generating a target to-do item according to the to-do item corresponding to the first to-do item entry or the second to-do item entry.

[0102] As mentioned above, the keyword includes a target keyword, and the target keyword is used to represent the information of the to-do item. Therefore, in the embodiments of the present application, generating the target to-do item in the target language type based on the keyword of the first language type is mainly generating the target to-do item based on the target keyword.

[0103] It should be noted that the difference between the keyword of the first language type and the target keyword is that usually the keyword of the first language type can include all nouns in a piece of text information containing the to-do item, while the target keyword only includes the nouns used to represent the information of the to-do item. For example, it is a sunny day on x year x month x day, there is a campsite in Park A, and go camping in Park A. In this passage, the first language keyword is x year x month x day, sunny day, Park A, campsite, camping, while the target keyword is x year x month x day, Park A, camping. It can be seen that the target keyword usually includes at least time, place, matter, and sometimes also includes person and person's emotion.

[0104] As a possible implementation, generating a target to-do item in the target language type based on keywords in the first language type includes: when there are at least two target keywords in the keywords of the first language type, if at least two target keywords meet the preset conflict rules, then determine the target keyword that appears last in the target text information among at least two target keywords and generate a target to-do item based on the target keyword that appears last in the target text information.

[0105] Among them, the preset conflict rule is a rule set in advance for judging whether there is a conflict between at least two keywords.

[0106] That is, there may be target keywords with conflicts before and after in the voice information. For example, if the voice information is a multi-person conversation information and there is negotiation and refutation in the multi-person conversation information, there may be keywords that meet the preset conflict rules. Usually, when there is a multi-person conversation, the to-do item that appears in the last conversation is the to-do item determined by the multi-person negotiation. Therefore, it is more accurate to generate a target to-do item based on the target keyword that appears last in the target text information. For example, Speaker 1 says "Go on a picnic in the park on a1 year, a2 month, a3 day", Speaker 2 says "It's raining that day, don't want to go, want to go for coffee", Speaker 1 says "Okay, where to go for coffee", Speaker 2 says "Go to yy coffee shop". The target keywords among them include: a1 year, a2 month, a3 day, park, picnic, don't want to go, that day, coffee, okay, yy coffee shop. Therefore, generate a to-do item according to the target keyword that appears last, and the finally generated to-do item is to go to the coffee shop for coffee on a1 year, a2 month, a3 day.

[0107] As a possible implementation, the preset conflict rules include: at least one of a keyword with a preset negative word and the information of the to-do items represented by at least two target keywords having partial repetition.

[0108] In some embodiments, the keywords with preset negative words include at least one of the keywords containing "not", "didn't", "don't", "do not", "never". For example, "don't want to go" in the above text is a negative word.

[0109] In some embodiments, at least one of the information of the to-do items represented by at least two target keywords having partial repetition includes: the information of the to-do items represented by at least two target keywords has time repetition and different locations. That is, no one can do two things at the same time. For example, "a1 year, a2 month, a3 day", "that day", "park", "coffee shop" in the above text are negative words.

[0110] As a possible implementation, generating a target to-do item of the target language type based on keywords of the first language type includes: when there are at least two target keywords among the keywords of the first language type, if the at least two target keywords do not conform to the preset conflict rule, then generating a target to-do item of the target language type based on the at least two keywords of the first language type.

[0111] That is, if the at least two target keywords do not conform to the preset conflict rule, it means that there is no part of negotiation or refutation regarding the to-do item in the voice information. Therefore, it is possible to directly generate a target to-do item of the target language type based on the at least two keywords of the first language type.

[0112] In some embodiments, after step S103, that is, after generating a target to-do item of the target language type based on keywords of the first language type, it further includes: generating a target to-do item reminder in an application based on the target to-do item. The application can be, for example, an alarm clock, a calendar, etc.

[0113] See Figure 4 for a schematic diagram of a to-do item generation device provided by an embodiment of the present application, as Figure 3 shown, the device includes:

[0114] An acquisition unit 401, configured to acquire target text information, where the target text information is the text information obtained when the to-be-processed voice information is converted from the voice type to the text type, and is expressed in the first language type; the to-be-processed voice information includes first voice information and second voice information, the first voice information is voice information of the second language type, the second voice information is voice information of the third language type, and the second language type is different from the third language type;

[0115] A processing unit 402, configured to determine keywords of the first language type according to the target text information; the keywords include target keywords, and the target keywords are used to characterize information about the to-do item; generating a target to-do item of the target language type based on the keywords of the first language type.

[0116] As a possible implementation, the acquisition unit 401 is specifically configured to: acquire the to-be-processed voice information; convert the to-be-processed voice information into text information of the target language type to obtain first target text information.

[0117] As a possible implementation, the acquisition unit 401 is specifically configured to: receive second target text information sent by other devices.

[0118] As a possible implementation, the processing unit 402 is specifically configured to: when the first language type is the same as the target language type, generate a to-do item of the target language type based on the keywords of the first language type.

[0119] As a possible implementation, the processing unit 402 is specifically configured to: when the first language type is different from the target language type, convert the keywords based on the first language type into keywords of the target language type, and generate a target to-do item of the target language type based on the keywords of the target language type.

[0120] As a possible implementation, the processing unit 402 is specifically configured to: determine the first keyword of the target voice type according to the first target text information; determine the second keyword of the first voice type according to the second target text information.

[0121] As a possible implementation, the processing unit 402 is specifically configured to: generate a first to-do item of the target language type based on the first keyword of the target voice type; generate a second to-do item of the target language type based on the second keyword of the first voice type; when the first to-do item is the same as the second to-do item, use the first to-do item of the target language type as the target to-do item.

[0122] As a possible implementation, the processing unit 402 is specifically configured to: when the first to-do item is different from the second to-do item, feed back the first to-do item and the second to-do item to the user.

[0123] As a possible implementation, the processing unit 402 is specifically configured to: when there are at least two target keywords for the keywords of the first language type, if at least two target keywords meet the preset conflict rule, determine the target keyword that appears last in the target text information among at least two target keywords and generate a target to-do item based on the target keyword that appears last in the target text information; the preset conflict rule is a rule set in advance for determining whether there is a conflict between at least two keywords.

[0124] As a possible implementation, the processing unit 402 is specifically configured to: when there are at least two target keywords for the keywords of the first language type, if at least two target keywords do not meet the preset conflict rule, generate a target to-do item of the target language type based on at least two keywords of the first language type.

[0125] Corresponding to the above embodiments, the present application further provides an electronic device. Figure 5A schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device 500 may include: a processor 501, a memory 502, and a communication unit 503. These components communicate through one or more buses. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiments of the present invention. It can be a bus structure, a star structure, and may also include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0126] Among them, the communication unit 503 is used to establish a communication channel so that the electronic device can communicate with other devices. Receive user data sent by other devices or send user data to other devices.

[0127] The processor 501 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 502, and by calling data stored in the memory, it executes various functions of the electronic device and / or processes data. The processor may be composed of an integrated circuit (IC). For example, it may be composed of a single packaged IC, or may be composed of connecting multiple packaged ICs with the same or different functions. For example, the processor 501 may only include a central processing unit (CPU). In the embodiments of the present invention, the CPU may be a single operation core or may include multiple operation cores.

[0128] The memory 502 is used to store the execution instructions of the processor 501. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0129] When the execution instructions in the memory 502 are executed by the processor 501, the electronic device 500 can execute Figure 1 Some or all of the steps in the illustrated embodiments.

[0130] In a specific implementation, the present invention further provides a computer-readable storage medium. The computer storage medium can store a program which, when executed, can include some or all of the steps in the various embodiments of the method for generating to-do items provided by the present invention. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0131] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution in the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments of the present invention.

[0132] For the same or similar parts among the various embodiments in this specification, reference can be made to each other. In particular, for the device embodiments and the terminal embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference can be made to the description in the method embodiments.

Claims

1. A method for generating to-do items, characterized in that, it includes the following steps: Obtain target text information, where the target text information is the text information obtained when the to-be-processed voice information is converted from the voice type to the text type and is expressed in the first language type; the to-be-processed voice information includes first voice information and second voice information, the first voice information is voice information of the second language type, the second voice information is voice information of the third language type, and the second language type is different from the third language type; Determine keywords of the first language type according to the target text information; the keywords include target keywords, and the target keywords are used to characterize the information of the to-do items; Generate a target to-do item of the target language type based on the keywords of the first language type.

2. The method according to claim 1, characterized in that, the obtaining of the target text information includes: Obtain the to-be-processed voice information; Convert the to-be-processed voice information into text information of the target language type to obtain first target text information.

3. The method according to claim 1 or 2, characterized in that, the obtaining of the target text information includes: Receive second target text information sent by other devices.

4. The method according to claim 1, characterized in that, the generating of the to-do item of the target language type based on the keywords of the first language type includes: When the first language type is the same as the target language type, generate a to-do item of the target language type based on the keywords of the first language type.

5. The method according to claim 1, characterized in that, the generating of the to-do item of the target language type based on the keywords of the first language type includes: When the first language type is different from the target language type, convert the keywords of the first language type into keywords of the target language type, and generate a target to-do item of the target language type based on the keywords of the target language type.

6. The method according to claim 3, characterized in that, when the obtained target text information includes first target text information and second target text information, the determining of the keywords of the first language type according to the target text information includes: Determine first keywords of the target voice type according to the first target text information; Determine second keywords of the first voice type according to the second target text information; the generating of the target to-do item of the target language type based on the keywords of the first language type includes: Generate a first to-do item of the target language type based on the first keywords of the target voice type; Generate a second to-do item of the target language type based on the second keywords of the first voice type; When the first to-do item is the same as the second to-do item, use the first to-do item of the target language type as the target to-do item.

7. The method according to claim 6, characterized in that, it further includes: When the first to-do item is different from the second to-do item, feedback the first to-do item and the second to-do item to the user.

8. The method according to claim 1, It is characterized in that generating a target to-do item of a target language type based on the keywords of the first language type includes: when there are at least two target keywords in the keywords of the first language type, if the at least two target keywords conform to a preset conflict rule, then determine the target keyword that appears last in the target text information among the at least two target keywords, and generate a target to-do item based on the target keyword that appears last in the target text information; the preset conflict rule is a rule set in advance for judging whether there is a conflict between at least two keywords.

9. The method according to claim 8, It is characterized in that generating a target to-do item of a target language type based on the keywords of the first language type includes: when there are at least two target keywords in the keywords of the first language type, if the at least two target keywords do not conform to a preset conflict rule, then generate a target to-do item of a target language type based on the at least two keywords of the first language type.

10. The method according to claim 8 or 9, It is characterized in that the preset conflict rule includes: at least one of a keyword with a preset negative word and partial repetition of the information of the to-do items represented by at least two target keywords.

11. A to-do item generation device, It is characterized in that including: an acquisition unit, configured to acquire target text information, where the target text information is the text information obtained when the to-be-processed voice information is converted from a voice type to a text type and is expressed in a first language type; the to-be-processed voice information includes first voice information and second voice information, the first voice information is voice information of a second language type, the second voice information is voice information of a third language type, and the second language type is different from the third language type; a processing unit, configured to determine keywords of a first language type according to the target text information; the keywords include target keywords, and the target keywords are used to represent the information of to-do items; generate a target to-do item of a target language type based on the keywords of the first language type.

12. An electronic device, It is characterized in that including a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the method according to any one of claims 1-10.

13. A computer-readable storage medium, It is characterized in that the computer-readable storage medium includes a stored program, wherein when the program runs, it controls the device where the computer-readable storage medium is located to execute the method according to any one of claims 1-10.

Images