Method and apparatus for determining dialogue skill service, electronic device and storage medium

Abstract

The present disclosure provides a determination method and device of a dialogue skill service, an electronic device and a storage medium, relates to the technical field of computers, and particularly relates to the technical fields of artificial intelligence and voice technology. The specific implementation scheme is as follows: obtaining dialogue information to be processed; obtaining a skill service intervention rule matched with the dialogue information according to the dialogue information; determining a dialogue skill service corresponding to the skill service intervention rule according to the skill service intervention rule, so as to serve as the dialogue skill service of the dialogue information.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular to the technical field of artificial intelligence and speech technology, and especially relates to a method and apparatus for determining a dialog skill service, an electronic device and a storage medium. BACKGROUND

[0002] A complete dialog robot is often composed of multiple different dialog skill services, and the recall logic between multiple dialog skill services is usually controlled by a dialog director. In this process, the dialog director can use skill service distribution technology to determine the candidate dialog skill service corresponding to the user dialog request.

[0003] At present, the dialog director usually uses skill service distribution technology based on literal fuzzy matching to find skill keywords related to the user's dialog request in the database to determine the candidate dialog skill service corresponding to the dialog request. SUMMARY

[0004] The present disclosure provides a method and apparatus for determining a dialog skill service, an electronic device and a storage medium.

[0005] According to an aspect of the present disclosure, a method for determining a dialog skill service is provided, comprising:

[0006] obtaining dialog information to be processed;

[0007] According to the dialog information, obtaining a skill service intervention rule matched with the dialog information;

[0008] According to the skill service intervention rule, determining the dialog skill service corresponding to the skill service intervention rule as the dialog skill service of the dialog information.

[0009] According to another aspect of the present disclosure, a determination apparatus for a dialog skill service is provided, comprising:

[0010] an obtaining unit configured to obtain dialog information to be processed;

[0011] a matching unit configured to obtain a skill service intervention rule matched with the dialog information according to the dialog information;

[0012] a determining unit configured to determine the dialog skill service corresponding to the skill service intervention rule as the dialog skill service of the dialog information according to the skill service intervention rule.

[0013] According to still another aspect of the present disclosure, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory in communication with the at least one processor; wherein

[0016] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of the aspects and any possible implementation thereof as described above.

[0017] According to yet another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of the aspects and any possible implementation thereof as described above is provided.

[0018] According to yet another aspect of the present disclosure, a computer program product comprising a computer program which, when executed by a processor, implements the method of the aspects and any possible implementation thereof as described above is provided.

[0019] From the above technical solutions, it can be seen that the embodiments of the present disclosure acquire the dialogue information to be processed, and then acquire the skill service intervention rule matched with the dialogue information according to the dialogue information, so that the dialogue skill service corresponding to the skill service intervention rule can be determined according to the skill service intervention rule as the dialogue skill service of the dialogue information. Since the dialogue skill service intervention rule matched with the dialogue information is acquired to determine the dialogue skill service of the dialogue information, the dialogue skill service related to the dialogue information can be determined more quickly and accurately, and the accuracy and efficiency of the dialogue skill service distribution are improved, thereby guaranteeing the reliability of the dialogue service provided for the user.

[0020] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0022] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure;

[0023] Figure 2 is a schematic diagram of a type of skill service intervention rule according to the first embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram according to the second embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram according to the third embodiment of the present disclosure;

[0026] Figure 5 is a block diagram of an electronic device for implementing a determination method of a dialog skill service according to an embodiment of the disclosure. DETAILED DESCRIPTION

[0027] Exemplary embodiments of the disclosure are described herein with reference to the accompanying drawings, in which various specific details are set forth to assist in a thorough understanding of the embodiments of the disclosure. It will be understood by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the disclosure. Also, the description herein is merely provided to describe and explain the embodiments of the disclosure, and is not intended to limit the scope of the disclosure.

[0028] It is apparent that the described embodiments are merely part of the embodiments of the disclosure, and not all the embodiments. Based on the embodiments in the disclosure, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the disclosure.

[0029] It should be noted that the terminal device involved in the embodiments of the disclosure can include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and the like. The display device can include, but is not limited to, a personal computer, a television, and the like.

[0030] In addition, the term "and / or" in the embodiments of the disclosure is merely a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are in an "or" relationship.

[0031] The dialog skill service, i.e., the bot skill, can refer to the dialog capability in a certain scenario, for example, the weather skill is responsible for providing the dialog capability in the weather scenario, and the song ordering and take-out functions of the smart speaker are also two dialog skills.

[0032] The bot service can be a unified dialog service integrated by multiple dialog skill services, which can support multiple dialog skill services at the same time, for example, the parenting bot service supports music, story, ancient poetry, and encyclopedia dialog skill services at the same time.

[0033] Generally, the integration management of multiple dialogue skill services is implemented by a dialogue director, which can control the recall logic among multiple dialogue skill services. The recall logic can refer to performing semantic analysis on a received user dialogue request to obtain dialogue information, determining a candidate dialogue skill service corresponding to the dialogue information, and obtaining reply information fed back to the user based on the candidate dialogue skill service. In this process, the dialogue director can utilize skill service distribution technology to determine the candidate dialogue skill service corresponding to the dialogue information, and further utilize the candidate dialogue skill service to determine the reply information corresponding to the user dialogue request and fed back to the user.

[0034] Currently, the dialogue director generally utilizes skill service distribution technology based on literal fuzzy matching to find skill service keywords related to the user dialogue request in a database, so as to determine the candidate dialogue skill service corresponding to the dialogue request. However, the traditional skill service distribution technology based on literal fuzzy matching is prone to over-recall or under-recall. Under-recall refers to that when the keywords of a certain dialogue skill service are not sufficient, the skill service keywords related to the user dialogue request cannot be found in the database, and the dialogue skill service cannot be selected into the candidate dialogue skill service. Over-recall refers to that when some user dialogue requests match the keywords of a dialogue skill service, the dialogue skill service itself is mistakenly determined to belong to the candidate dialogue skill service due to completely different actual semantics. For example, the user dialogue request is “I want to watch the weather son”, which hits the keyword “weather” of the weather dialogue skill service, resulting in low accuracy of skill service distribution.

[0035] Therefore, it is urgent to provide a dialogue skill service determination method, which can quickly and accurately determine the dialogue skill service related to the dialogue information, so as to improve the efficiency and accuracy of dialogue skill service distribution.

[0036] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure, as Figure 1 shown.

[0037] 101, obtaining dialogue information to be processed.

[0038] 102, obtaining skill service intervention rules matched with the dialogue information according to the dialogue information.

[0039] 103, determining dialogue skill services corresponding to the skill service intervention rules as dialogue skill services of the dialogue information according to the skill service intervention rules.

[0040] At this point, the dialogue skill services of the dialogue information can be utilized to obtain reply information corresponding to the dialogue information, so as to feed back the reply information to the user sending the dialogue information to be processed.

[0041] It can be understood that the dialog skill service of the dialog information is a candidate dialog skill service corresponding to the dialog information. After obtaining the candidate dialog skill service, the dialog skill service distribution can be directly performed using the candidate dialog skill service, and the reply information corresponding to the dialog information can be determined using the candidate dialog skill service, and the reply information is fed back to the user to reply to the user.

[0042] It should be noted that the voice information sent by the user, i.e., the dialog request, can be obtained first. Then, the voice information sent by the user is subjected to voice recognition to obtain text information corresponding to the voice information. The text information is subjected to semantic analysis processing to obtain the dialog information to be processed corresponding to the text information.

[0043] It should be noted that the skill service intervention rule can be a preconfigured rule for intervening in the dialog skill service distribution. The skill service intervention rule and the dialog skill service can have a corresponding relationship, and then after obtaining the skill service intervention rule matched with the dialog information, the dialog skill service of the dialog information can be determined according to the corresponding relationship between the skill service intervention rule and the dialog skill service.

[0044] It should be noted that part or all of the execution subjects of 101-103 can be an application located in the local terminal, or can also be a plug-in or a software development kit (SDK) and the like functional units arranged in the application located in the local terminal, or can also be a processing engine located in a network side server, or can also be a distributed system located in the network side, such as a processing engine or a distributed system in a dialog service platform of the network side, and the like, which are not particularly limited in the embodiment.

[0045] It can be understood that the application can be a native application (nativeApp) installed on the local terminal, or can also be a web application (webApp) of a browser on the local terminal, which is not limited in the embodiment.

[0046] In this way, by obtaining the dialog information to be processed, the skill service intervention rule matched with the dialog information can be obtained according to the dialog information, so that the dialog skill service corresponding to the skill service intervention rule can be determined as the dialog skill service of the dialog information according to the skill service intervention rule. Since the dialog skill service of the dialog information is determined by using the obtained skill service intervention rule matched with the dialog information, the dialog skill service related to the dialog information can be determined more quickly and accurately, the accuracy and efficiency of the dialog skill service distribution are improved, and the reliability of the dialog service provided for the user is ensured.

[0047] Optionally, in one possible implementation of this embodiment, in step 102, at least one skill service intervention rule can be used to match the dialogue information in order to obtain a skill service intervention rule that matches the dialogue information.

[0048] In this implementation, the skill service intervention rule may include a specified type of skill service intervention rule determined according to the developer's business needs. Any specified type of skill service intervention rule may correspond to at least one conversational skill service; that is, any specified type of skill service intervention rule may have a correspondence with at least one conversational skill service. Any specified type of skill service intervention rule may include whitelist intervention rules and blacklist intervention rules. Whitelist intervention rules and blacklist intervention rules may each include at least one intervention rule, such as... Figure 2 As shown. For any given type of skill service intervention rule, any whitelist intervention rule may include information associated with the dialogue skill service corresponding to the given type of skill service intervention rule. Any blacklist intervention rule may include ambiguous information regarding the dialogue skill service corresponding to the given type of skill service intervention rule.

[0049] For example, the skills service intervention rules are for media asset-related skills services. These rules could correspond to skills services in music dialogue, film and television dialogue, and radio dialogue, etc. Figure 2 As shown. The whitelist and blacklist intervention rules for media asset-related skill services can each include multiple rules. One rule in the whitelist intervention rules for media asset-related skill services can be "Weathering With You," and one rule in the blacklist intervention rules for media asset-related skill services can be "Weather."

[0050] In one specific implementation of this approach, the at least one skill service intervention rule can be used to perform text-based matching on the dialogue information to obtain the skill service intervention rule that matches the dialogue information.

[0051] In this implementation process, the skills service intervention rules can include whitelist intervention rules and blacklist intervention rules.

[0052] In one implementation scenario, the whitelist intervention rule of the at least one skill service intervention rule can be used to perform text-based matching on the dialogue information. If the dialogue information matches any whitelist intervention rule, the skill service intervention rule that matches the dialogue information can be obtained.

[0053] In another scenario of this implementation process, the blacklist intervention rule of the at least one skill service intervention rule can be used to perform text-based matching on the dialogue information. If the dialogue information matches any blacklist intervention rule, then the skill service intervention rule that matches the dialogue information cannot be obtained.

[0054] In another specific implementation of this approach, the at least one skill service intervention rule can be used to perform regular expression-based matching on the dialogue information to obtain the skill service intervention rule that matches the dialogue information.

[0055] In one implementation scenario, the whitelist intervention rule of the at least one skill service intervention rule can be used to perform regular expression matching on the dialogue information. If the dialogue information matches any whitelist intervention rule, the skill service intervention rule that matches the dialogue information can be obtained.

[0056] In another scenario of this implementation process, the blacklist intervention rule of the at least one skill service intervention rule can be used to match the dialogue information based on regular expressions. If the dialogue information matches any blacklist intervention rule, then the skill service intervention rule that matches the dialogue information cannot be obtained.

[0057] Specifically, text-based matching can represent a perfect match with the intervention rule. Regular expression-based matching can represent a fuzzy match with the intervention rule.

[0058] In this way, by utilizing skill service intervention rules, the dialogue information is matched based on text and / or regular expressions to obtain the skill service intervention rules that match the dialogue information. Since the matching processing of dialogue information supports different types of matching methods, the matching processing means are enriched, thus enabling the skill service intervention rules that match the dialogue information to be obtained more quickly and effectively.

[0059] In another specific implementation of this approach, the pre-configured skill service may include multiple specified types of skill service intervention rules. Each specified type of skill service intervention rule can be further used to match the dialogue information to obtain the skill service intervention rule that matches the dialogue information in each specified type.

[0060] Understandably, in subsequent execution 103, the dialogue skill service corresponding to the skill service intervention rule matching the dialogue information in each specified type can be determined based on the skill service intervention rule matching the dialogue information in each specified type. Then, the dialogue skill services in each specified type are subjected to union processing to serve as the dialogue skill service of the dialogue information.

[0061] In another specific implementation of this approach, at least one whitelist intervention rule can be used to match the dialogue information. If the dialogue information matches any whitelist intervention rule, the skill service intervention rule that matches the dialogue information can be obtained, meaning that the dialogue information and the skill service intervention rule are successfully matched.

[0062] Alternatively, the dialogue information can be matched using at least one blacklist intervention rule. If the dialogue information matches any blacklist intervention rule, the skill service intervention rule that matches the dialogue information cannot be obtained. That is, the dialogue information fails to match the skill service intervention rule, and no skill service intervention rule that matches the dialogue information is obtained.

[0063] Alternatively, at least one whitelist intervention rule can be used to match the dialogue information. If the dialogue information does not match any whitelist intervention rule, then the skill service intervention rule matching the dialogue information cannot be obtained. That is, the dialogue information fails to match the skill service intervention rule, and no skill service intervention rule matching the dialogue information is obtained.

[0064] In this way, the implementation method uses at least one skill service intervention rule to match the acquired dialogue information to obtain the skill service intervention rule that matches the dialogue information. Then, based on the matched skill service intervention rule, the dialogue skill service of the dialogue information can be determined. This allows for faster and more accurate identification of the dialogue skill service related to the dialogue information, improving the accuracy and efficiency of dialogue skill service distribution, and thus ensuring the reliability of the dialogue service provided to users.

[0065] Furthermore, by utilizing blacklists and whitelists in multiple skill service intervention rules to match the acquired dialogue information, it is possible to quickly obtain the skill service intervention rules that match the dialogue information, thereby further improving the accuracy and efficiency of dialogue skill service distribution.

[0066] Optionally, in one possible implementation of this embodiment, if no skill service intervention rule matching the dialogue information is obtained in step 102, the dialogue information is subjected to dialogue skill service classification processing to obtain a dialogue skill service classification result, and then the dialogue skill service corresponding to the dialogue information can be determined based on the dialogue skill service classification result.

[0067] In this implementation, the skill service intervention rules can include whitelist intervention rules and blacklist intervention rules. If the dialogue information does not match any whitelist intervention rule, it can be determined that no skill service intervention rule matching the dialogue information has been obtained; or, if the dialogue information matches any blacklist intervention rule, it can be determined that no skill service intervention rule matching the dialogue information has been obtained.

[0068] In one specific implementation of this approach, a preset classification model can be used to classify the dialogue information into dialogue skill services to obtain the dialogue skill service classification results.

[0069] Specifically, the preset classification model can be determined by training a model using a neural network algorithm based on custom training data. The preset classification model can include classifiers for dialogue skill services of multiple skill service types. For any dialogue skill service classifier, the classifier can be determined by training a model using a neural network algorithm based on custom training data for that dialogue skill service. This custom training data can be training data uploaded by the developer based on the dialogue customization interface.

[0070] Here, the classification result of dialogue skills services can be the type of dialogue skills service corresponding to the dialogue information, that is, the dialogue skills service corresponding to the dialogue information. Therefore, based on the classification result of dialogue skills services, the dialogue skills service corresponding to the dialogue information can be obtained, that is, the candidate dialogue skills service for dialogue skills service distribution.

[0071] In this way, if no skill service intervention rule matching the dialogue information is obtained, the dialogue information can be classified into dialogue skill services by using a preset classification model, and then determined based on the obtained dialogue skill service classification results. Since the preset classification model is used to determine the dialogue skill service corresponding to the dialogue information, the generalization ability of dialogue skill service distribution can be further improved, thereby reducing the workload of manually configuring dialogue skill services.

[0072] In another specific implementation of this approach, preset skill type keywords can be used to classify the dialogue information into dialogue skill service categories to obtain dialogue skill service classification results.

[0073] It is understandable that if no skill service intervention rule matching the dialogue information is obtained, other existing classification methods can be used to classify the dialogue information into dialogue skills services in order to obtain the dialogue skills service classification result.

[0074] In this way, if no skill service intervention rule matching the dialogue information is obtained, the dialogue information can be classified into dialogue skill services, and then the dialogue skill service corresponding to the dialogue information can be determined based on the classification result. The determined dialogue skill service can then be used for dialogue skill service distribution, thereby ensuring the reliability of dialogue skill service distribution.

[0075] It should be noted that the various specific implementation processes provided in the aforementioned implementation methods can be combined with the various specific implementation processes provided in this implementation method to determine the dialogue skill service corresponding to the dialogue information. Detailed descriptions can be found in the relevant content of the aforementioned implementation methods, and will not be repeated here.

[0076] Optionally, in one possible implementation of this embodiment, before step 101, the skill service intervention rules and the correspondence between the dialogue skill services can be configured in response to the developer's operation based on the custom dialogue interface.

[0077] In this implementation, in response to the developer's custom dialogue interface operation, skill service intervention rules, dialogue skill services, and the correspondence between the skill service intervention rules and the dialogue skill services can be configured. Therefore, in step 103, the dialogue skill service for the dialogue information can be determined based on the skill service intervention rules matched with the dialogue skill service and the correspondence between the dialogue skill services.

[0078] Specifically, the skill service intervention rule can include a specified type of skill service intervention rule configured according to the developer's business needs. For any specified type of skill service intervention rule, in response to the developer's custom dialog interface operation, the mapping relationship between the specified type of skill service intervention rule and at least one dialog skill service can be configured. The skill service intervention rule can include developer-defined whitelist intervention rules and blacklist intervention rules. The whitelist intervention rules and blacklist intervention rules can each include at least one intervention rule, such as... Figure 2 As shown.

[0079] Specifically, for any given type of skill service intervention rule, the whitelist intervention rule may include information defined by the developer that is associated with the conversational skill service corresponding to the specified type of skill service intervention rule. The blacklist intervention rule may include information defined by the developer that is ambiguous with the conversational skill service corresponding to the specified type of skill service intervention rule.

[0080] In this way, by responding to the developer's custom dialogue interface operations and configuring information such as skill service intervention rules and the correspondence between dialogue skill services, this implementation method can determine the skill service intervention rules based on the developer's business needs, and then determine the dialogue skill service corresponding to the acquired dialogue information to be processed based on the skill service intervention rules, thereby completing the distribution of dialogue skill services. This can effectively meet the needs of developers and improve the controllability of dialogue skill service distribution.

[0081] It should be noted that after configuring the relevant correspondences according to this implementation method, the dialogue skill service for dialogue information can be determined by combining the various specific implementation processes provided in the aforementioned implementation method. Detailed descriptions can be found in the relevant content of the aforementioned implementation method, and will not be repeated here.

[0082] In this embodiment, by acquiring the dialogue information to be processed, a skill service intervention rule matching the dialogue information can be obtained. This allows the dialogue skill service corresponding to the skill service intervention rule to be determined as the dialogue skill service for the dialogue information. Since the dialogue skill service for the dialogue information is determined by using the acquired skill service intervention rule matching the dialogue information, the dialogue skill service related to the dialogue information can be determined more quickly and accurately, improving the accuracy and efficiency of dialogue skill service distribution, thereby ensuring the reliability of the dialogue service provided to the user.

[0083] Furthermore, by employing the technical solution provided in this embodiment, the acquired dialogue information can be matched using at least one skill service intervention rule to obtain the skill service intervention rule that matches the dialogue information. Then, the dialogue skill service of the dialogue information can be determined based on the matched skill service intervention rule. This allows for faster and more accurate determination of the dialogue skill service related to the dialogue information, improving the accuracy and efficiency of dialogue skill service distribution, and thus ensuring the reliability of the dialogue service provided to users.

[0084] In addition, by using the technical solution provided in this embodiment, the skill service intervention rules can also be used to match the dialogue information based on text and / or regular expressions to obtain the skill service intervention rules that match the dialogue information. Since the matching processing of dialogue information supports different types of matching methods, the matching processing means are enriched, thereby enabling the skill service intervention rules that match the dialogue information to be obtained more quickly and effectively.

[0085] In addition, if no skill service intervention rule matching the dialogue information is obtained by using the technical solution provided in this embodiment, the dialogue information can be classified into dialogue skill services, and then the dialogue skill service corresponding to the dialogue information can be determined according to the classification result. That is, the determined dialogue skill service can be used to distribute the dialogue skill service, thereby ensuring the reliability of the dialogue skill service distribution.

[0086] In addition, if the technical solution provided in this embodiment does not obtain the skill service intervention rule that matches the dialogue information, the dialogue information can be classified into dialogue skill services by using a preset classification model, and then determined according to the obtained dialogue skill service classification result. Since the preset classification model is used to determine the dialogue skill service corresponding to the dialogue information, the generalization ability of dialogue skill service distribution can be further improved, thereby reducing the workload of manually configuring dialogue skill services.

[0087] Furthermore, by adopting the technical solution provided in this embodiment, and by responding to the operations of the developer's custom dialogue interface, configuring information such as skill service intervention rules and the correspondence between dialogue skill services, it is possible to determine skill service intervention rules based on the developer's business needs, and then determine the dialogue skill service corresponding to the acquired dialogue information to be processed based on the skill service intervention rules, thereby completing the distribution of dialogue skill services. This can effectively meet the needs of developers and improve the controllability of dialogue skill service distribution.

[0088] In addition, by adopting the technical solution provided in this embodiment, it is possible to quickly and accurately reply to users with response information corresponding to the dialogue information, thereby improving the user experience.

[0089] Figure 3 This is a schematic diagram based on the second embodiment of the present disclosure, as shown below. Figure 3 As shown.

[0090] 301. Obtain the dialogue information to be processed.

[0091] Specifically, the process can begin by acquiring the user's voice message, i.e., the dialogue request. Then, speech recognition is performed on the user's voice message to obtain the corresponding text information. Finally, semantic parsing is performed on the text information to obtain the dialogue information to be processed.

[0092] 302. Obtain pre-configured skill service intervention rules.

[0093] Specifically, it can respond to the developer's custom interface dialogue operations, configure skill service intervention rules, dialogue skill services, and the correspondence between skill service intervention rules and dialogue skill services.

[0094] Specifically, the pre-configured skill service intervention rules can include specified types of skill service intervention rules configured according to the developer's business needs. For any specified type of skill service intervention rule, in response to the developer's custom dialog interface operation, the mapping relationship between that specified type of skill service intervention rule and at least one dialog skill service can be configured. These skill service intervention rules can include developer-defined whitelist intervention rules and blacklist intervention rules. Each whitelist and blacklist intervention rule can each include at least one intervention rule.

[0095] Specifically, for any given type of skill service intervention rule, the whitelist intervention rule may include information defined by the developer that is associated with the conversational skill service corresponding to the specified type of skill service intervention rule. The blacklist intervention rule may include information defined by the developer that is ambiguous with the conversational skill service corresponding to the specified type of skill service intervention rule.

[0096] 303. Match the dialogue information with the pre-configured skill service intervention rules to obtain the matching results.

[0097] 304. Determine the matching result.

[0098] In one scenario, if the matching result is a pre-configured skill service intervention rule that matches the dialogue information, then a 305 error is executed.

[0099] Specifically, if the dialogue information matches any whitelist intervention rule, then the pre-configured skill service intervention rule that matches the dialogue information can be obtained, that is, the pre-configured skill service intervention rule that matches the dialogue information can be obtained.

[0100] In another scenario, if the matching result is that no pre-configured skill service intervention rule matching the dialogue information is found, then a 306 error is executed.

[0101] Specifically, if the dialogue information does not match any whitelist intervention rule, then the pre-configured skill service intervention rule matching the dialogue information cannot be obtained; that is, no pre-configured skill service intervention rule matching the dialogue information is obtained. Alternatively, if the dialogue information matches any blacklist intervention rule, then the pre-configured skill service intervention rule matching the dialogue information cannot be obtained; that is, no pre-configured skill service intervention rule matching the dialogue information is obtained.

[0102] 305. Determine the dialogue skill service corresponding to the pre-configured skill service intervention rule that matches the dialogue information, and use it as the dialogue skill service for the dialogue information.

[0103] 306. Using a pre-defined classification model, classify the dialogue information into dialogue skills services to obtain the dialogue skills service classification results.

[0104] 307. Based on the classification results of dialogue skills services, determine the dialogue skills services corresponding to the dialogue information.

[0105] Specifically, the preset classification model can be determined by training a model using a neural network algorithm based on custom training data. The preset classification model can include classifiers for dialogue skill services of multiple skill service types. For any dialogue skill service classifier, the classifier can be determined by training a model using a neural network algorithm based on custom training data for that dialogue skill service. This custom training data can be training data uploaded by the developer based on the dialogue customization interface.

[0106] Here, a pre-defined classification model can be used to identify the classification result of the dialogue skill service corresponding to the dialogue information. The classification result of the dialogue skill service can include at least one dialogue skill service. Based on the classification result of the dialogue skill service corresponding to the dialogue information, at least one dialogue skill service corresponding to the dialogue information can be determined.

[0107] By employing the technical solution provided in this embodiment, the dialogue skill services of the dialogue information can be determined by utilizing the skill service intervention rules that match the acquired dialogue information. This allows for faster and more accurate identification of dialogue skill services related to the dialogue information, improving the accuracy and efficiency of dialogue skill service distribution and thus ensuring the reliability of the dialogue services provided to users.

[0108] Furthermore, if no skill service intervention rules matching the dialogue information are obtained, the dialogue information can be classified into dialogue skill services by using a preset classification model. Then, the dialogue skill service is determined based on the obtained dialogue skill service classification results. Since the preset classification model is used to determine the dialogue skill service corresponding to the dialogue information, the generalization ability of dialogue skill service distribution can be further improved, thereby reducing the workload of manually configuring dialogue skill services.

[0109] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0110] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0111] Figure 4 This is a schematic diagram based on the third embodiment of the present disclosure, as shown below. Figure 4 As shown. The device 400 for determining dialogue skill services in this embodiment may include an acquisition unit 401, a matching unit 402, and a determination unit 403. The acquisition unit 401 is used to acquire dialogue information to be processed; the matching unit 402 is used to acquire a skill service intervention rule matching the dialogue information; and the determination unit 403 is used to determine the dialogue skill service corresponding to the skill service intervention rule, based on the skill service intervention rule, as the dialogue skill service for the dialogue information.

[0112] It should be noted that some or all of the device for determining the dialogue skill service in this embodiment may be an application located on a local terminal, or it may be a plugin or software development kit (SDK) or other functional unit set in an application located on a local terminal, or it may be a processing engine located on a network-side server, or it may be a distributed system located on the network side, such as a processing engine or distributed system in a dialogue service platform on the network side. This embodiment does not impose any particular limitations on this.

[0113] It is understood that the application may be a native program installed on the local terminal, or it may be a web application of a browser on the local terminal. This embodiment does not limit this.

[0114] Optionally, in one possible implementation of this embodiment, the matching unit 402 may be specifically used to perform matching processing on the dialogue information using at least one skill service intervention rule, so as to obtain the skill service intervention rule that matches the dialogue information.

[0115] For example, the matching unit 402 can also be further used to perform text-based matching on the dialogue information using at least one skill service intervention rule to obtain the skill service intervention rule that matches the dialogue information.

[0116] Alternatively, for example, the matching unit 402 can be further used to perform regular expression-based matching on the dialogue information using at least one skill service intervention rule to obtain the skill service intervention rule that matches the dialogue information.

[0117] Optionally, in one possible implementation of this embodiment, the determining unit 403 may be further configured to perform dialogue skill service classification processing on the dialogue information if no skill service intervention rule matching the dialogue information is obtained, so as to obtain a dialogue skill service classification result; and determine the dialogue skill service corresponding to the dialogue information based on the dialogue skill service classification result.

[0118] Optionally, in one possible implementation of this embodiment, the determining unit 403 can be specifically used to classify the dialogue information into dialogue skill services using a preset classification model to obtain dialogue skill service classification results.

[0119] Optionally, in one possible implementation of this embodiment, the acquisition unit 401 may further be used to configure the correspondence between the skill service intervention rules and the dialogue skill service in response to the developer's operation based on the dialog custom interface.

[0120] In this embodiment, the acquisition unit acquires the dialogue information to be processed, and then the matching unit acquires the skill service intervention rule matching the dialogue information. The determination unit then determines the dialogue skill service corresponding to the skill service intervention rule as the dialogue skill service of the dialogue information. Since the dialogue skill service of the dialogue information is determined by using the acquired skill service intervention rule matching the dialogue information, the dialogue skill service related to the dialogue information can be determined more quickly and accurately, improving the accuracy and efficiency of dialogue skill service distribution, thereby ensuring the reliability of the dialogue service provided to the user.

[0121] Furthermore, by employing the technical solution provided in this embodiment, the acquired dialogue information can be matched using at least one skill service intervention rule to obtain the skill service intervention rule that matches the dialogue information. Then, the dialogue skill service of the dialogue information can be determined based on the matched skill service intervention rule. This allows for faster and more accurate determination of the dialogue skill service related to the dialogue information, improving the accuracy and efficiency of dialogue skill service distribution, and thus ensuring the reliability of the dialogue service provided to users.

[0122] In addition, by using the technical solution provided in this embodiment, the skill service intervention rules can also be used to match the dialogue information based on text and / or regular expressions to obtain the skill service intervention rules that match the dialogue information. Since the matching processing of dialogue information supports different types of matching methods, the matching processing means are enriched, thereby enabling the skill service intervention rules that match the dialogue information to be obtained more quickly and effectively.

[0123] In addition, if no skill service intervention rule matching the dialogue information is obtained by using the technical solution provided in this embodiment, the dialogue information can be classified into dialogue skill services, and then the dialogue skill service corresponding to the dialogue information can be determined according to the classification result. That is, the determined dialogue skill service can be used to distribute the dialogue skill service, thereby ensuring the reliability of the dialogue skill service distribution.

[0124] In addition, if the technical solution provided in this embodiment does not obtain the skill service intervention rule that matches the dialogue information, the dialogue information can be classified into dialogue skill services by using a preset classification model, and then determined according to the obtained dialogue skill service classification result. Since the preset classification model is used to determine the dialogue skill service corresponding to the dialogue information, the generalization ability of dialogue skill service distribution can be further improved, thereby reducing the workload of manually configuring dialogue skill services.

[0125] Furthermore, by adopting the technical solution provided in this embodiment, and by responding to the operations of the developer's custom dialogue interface, configuring information such as skill service intervention rules and the correspondence between dialogue skill services, it is possible to determine skill service intervention rules based on the developer's business needs, and then determine the dialogue skill service corresponding to the acquired dialogue information to be processed based on the skill service intervention rules, thereby completing the distribution of dialogue skill services. This can effectively meet the needs of developers and improve the controllability of dialogue skill service distribution.

[0126] In addition, by adopting the technical solution provided in this embodiment, it is possible to quickly and accurately reply to users with response information corresponding to the dialogue information, thereby improving the user experience.

[0127] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with relevant laws and regulations and do not violate public order and good morals.

[0128] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0129] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0130] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0131] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0132] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the method for determining a conversational skills service. For example, in some embodiments, the method for determining a conversational skills service may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the method for determining a conversational skills service described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the method for determining a conversational skills service by any other suitable means (e.g., by means of firmware).

[0133] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0137] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0138] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0139] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0140] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining a dialog skill service, comprising: obtaining dialog information to be processed; obtaining, according to the dialog information, a skill service intervention rule matched with the dialog information; determining, according to a preconfigured correspondence between the skill service intervention rule and a dialog skill service, the dialog skill service corresponding to the skill service intervention rule as the dialog skill service of the dialog information; obtaining, according to the dialog information, a skill service intervention rule matched with the dialog information, comprising: performing text-based matching on the dialog information by using a whitelist intervention rule of at least one candidate skill service intervention rule; if the dialog information hits a target whitelist intervention rule, determining that the target whitelist intervention rule is the skill service intervention rule matched with the dialog information.

2. The method of claim 1, wherein, The step of obtaining, according to the dialog information, a skill service intervention rule matched with the dialog information can also be implemented in the following manner: performing regular expression-based matching on the dialog information by using the at least one skill service intervention rule to obtain the skill service intervention rule matched with the dialog information.

3. The method of any one of claims 1-2, wherein, The method further comprises: if no skill service intervention rule matched with the dialog information is obtained, performing dialog skill service classification processing on the dialog information to obtain a dialog skill service classification result; determining the dialog skill service corresponding to the dialog information according to the dialog skill service classification result.

4. The method of claim 3, wherein, The step of performing dialog skill service classification processing on the dialog information to obtain a dialog skill service classification result comprises: performing dialog skill service classification on the dialog information by using a preset classification model to obtain the dialog skill service classification result.

5. The method of any one of claims 1-4, wherein, Before the step of obtaining dialog information to be processed, the method further comprises: in response to an operation of a developer based on a dialog custom interface, configuring the correspondence between the skill service intervention rule and the dialog skill service.

6. A device for determining a dialog skill service, comprising: an obtaining unit configured to obtain dialog information to be processed; a matching unit configured to obtain, according to the dialog information, a skill service intervention rule matched with the dialog information; a determining unit configured to determine, according to a preconfigured correspondence between the skill service intervention rule and a dialog skill service, the dialog skill service corresponding to the skill service intervention rule as the dialog skill service of the dialog information; The matching unit is configured to: perform text-based matching on the dialog information by using a whitelist intervention rule of at least one candidate skill service intervention rule; if the dialog information hits a target whitelist intervention rule, determine that the target whitelist intervention rule is the skill service intervention rule matched with the dialog information.

7. The apparatus of claim 6, wherein, The matching unit can also be configured to implement the following steps: perform regular expression-based matching on the dialog information by using the at least one skill service intervention rule to obtain the skill service intervention rule matched with the dialog information.

8. The apparatus of any one of claims 6-7, wherein, The determining unit is further configured to If no skill service intervention rule matched with the dialogue information is acquired, the dialogue information is subjected to dialogue skill service classification processing to obtain a dialogue skill service classification result. According to the dialogue skill service classification result, a dialogue skill service corresponding to the dialogue information is determined.

9. The apparatus of claim 8, wherein, The determining unit is specifically configured to The dialogue information is subjected to dialogue skill service classification by using a preset classification model to obtain a dialogue skill service classification result.

10. The apparatus of any one of claims 6-9, wherein, The acquiring unit is further configured to In response to an operation of a developer based on a dialogue customized interface, a correspondence between the skill service intervention rule and the dialogue skill service is configured. 11.An electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication;wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-5.

12. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method according to any one of claims 1-5. 13.A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-5.

Images