WO2021217915A1

WO2021217915A1 - Human-machine dialog method and apparatus, and computer device and storage medium

Info

Publication number: WO2021217915A1
Application number: PCT/CN2020/103847
Authority: WO
Inventors: 邹倩霞; 徐国强
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2020-04-28
Filing date: 2020-07-23
Publication date: 2021-11-04
Also published as: CN111552779A

Abstract

A human-machine dialog method and apparatus, and a computer device and a storage medium, which relate to the field of data processing of artificial intelligence. The method is executed by a framework with a configurable parameter extraction function. The method comprises: after a dialog platform starts a dialog with a user, executing a text information acquisition step, wherein the text information acquisition step comprises acquiring dialog text information, provided by the dialog platform, of the user (220), wherein the dialog text information is generated by the dialog platform according to dialog data and is provided to a framework; extracting a parameter of the dialog text information on the basis of a pre-configured parameter extraction function (230); sending the extracted parameter of the dialog text information to the dialog platform, such that the dialog platform continues the dialog with the user according to the parameter (250); and executing the text information acquisition step until a dialog between the dialog platform and the user is stopped (260). According to the method, the use efficiency of a human-machine dialog platform is improved, the use of the dialog platform can be more convenient, and the requirements of more scenarios can be met.

Description

Man-machine dialogue method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on April 28, 2020, the application number is CN 202010350529.1, and the invention title is "Human-Machine Dialogue Methods, Devices, Media, and Electronic Equipment", the entire content of which is incorporated by reference Incorporated in this application.

Technical field

This application relates to the field of artificial intelligence data processing technology, in particular to a human-machine dialogue method, device, computer equipment, and computer-readable storage medium.

Background technique

At present, in the field of artificial intelligence technology, human-machine dialogue platforms are frequently adopted. In the prior art, when a multi-round human-machine dialogue platform is applied, it is necessary to process and process the user’s dialogue information and extract the corresponding key information. Realize accurate man-machine dialogue. However, the inventor realizes that the types of key information that can be extracted by the current human-machine dialogue platform are limited, and cannot meet the needs of extracting more types of key information; if it is necessary to extract more types of key information, such as extracting financial fields, macro The key information related to the economic direction requires developers to continuously develop new functions to meet the needs of different businesses in various fields. Therefore, the current human-machine dialogue platform is inefficient and not convenient to use.

Summary of the invention

In the field of artificial intelligence data processing technology, in order to solve the above technical problems, the purpose of this application is to provide a human-machine dialogue method, device, computer equipment, and computer-readable storage medium.

In the first aspect, a human-machine dialogue method is provided. The method is executed by a framework with a configurable parameter extraction function, including:

After the dialogue platform starts a dialogue with the target user, a step of obtaining text information is performed. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform, and the dialogue text information is determined by the dialogue The platform generates and provides the framework with the configurable parameter extraction function according to the dialogue data of the target user;

Extract the parameters of the dialogue text information based on the pre-configured parameter extraction function;

Sending the extracted parameters of the dialogue text information to the dialogue platform for the dialogue platform to continue the dialogue with the target user according to the parameters;

The step of obtaining text information is performed until the dialogue between the dialogue platform and the target user is stopped.

In the second aspect, a human-machine dialogue method is provided, which is executed by a dialogue platform, and includes:

During a dialogue with a target user, obtain dialogue data of the target user, and generate dialogue text information based on the dialogue data;

The dialog text information is provided to the framework of the configurable parameter extraction function, so that the framework of the configurable parameter extraction function extracts the parameters of the dialog text information based on the pre-configured parameter extraction function, and receives the The parameters of the dialogue text information obtained by frame extraction;

Continue the dialogue with the target user according to the parameters, and continue to execute the step of obtaining dialogue data of the target user and generating dialogue text information based on the dialogue data, until the dialogue with the target user stops .

In a third aspect, a human-machine dialogue device is provided, the device includes a framework with a configurable parameter extraction function, and the device includes:

The obtaining module is configured to execute the step of obtaining text information after the dialogue platform starts a dialogue with the target user. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform. The text information is generated by the dialogue platform according to the dialogue data of the target user and provided to the framework with configurable parameter extraction function;

The parameter extraction module is configured to extract the parameters of the dialog text information based on a pre-configured parameter extraction function;

A sending module, configured to send the extracted parameters of the dialogue text information to the dialogue platform, so that the dialogue platform can continue the dialogue with the target user according to the parameters;

The execution module is configured to execute the step of obtaining text information until the dialogue between the dialogue platform and the target user stops.

In a fourth aspect, a computer device is provided, including a memory and a processor, the memory is used to store a program of the human-machine dialogue of the processor, and the processor is configured to execute the program of the human-machine dialogue. The following processing is performed: after the dialogue platform starts a dialogue with the target user, the step of obtaining text information is performed, and the step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform, the dialogue text information Generated by the dialogue platform according to the dialogue data of the target user and provided to the framework with configurable parameter extraction function; based on the pre-configured parameter extraction function, the parameters of the dialogue text information are extracted; the extracted result The parameters of the dialogue text information are sent to the dialogue platform for the dialogue platform to continue the dialogue with the target user according to the parameters; the step of obtaining text information is performed until the dialogue platform and the target The conversation between users stops.

In a fifth aspect, a computer device is provided, including a memory and a processor, the memory is configured to store a program of the human-machine dialogue of the processor, and the processor is configured to execute the program of the human-machine dialogue The following processing is performed: during a dialogue with the target user, the dialogue data of the target user is obtained, and dialogue text information is generated based on the dialogue data; the dialogue text information is provided to the framework of the configurable parameter extraction function for use The framework of the configurable parameter extraction function extracts the parameters of the dialogue text information based on the pre-configured parameter extraction function, and receives the parameters of the dialogue text information extracted by the framework; The target user continues to have a dialogue, and continues to perform the steps of obtaining dialogue data of the target user and generating dialogue text information based on the dialogue data until the dialogue with the target user stops.

In a sixth aspect, a computer-readable storage medium storing computer-readable instructions is provided, and a program for man-machine dialogue is stored thereon. When the program for the man-machine dialogue is executed by a processor, the following processing is implemented: After the target user starts the dialogue, the step of obtaining text information is executed. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform, and the dialogue text information is determined by the dialogue platform according to the The dialog data of the target user is generated and provided to the framework with a configurable parameter extraction function; the parameters of the dialog text information are extracted based on the pre-configured parameter extraction function; the parameters of the extracted dialog text information are extracted Send to the dialogue platform for the dialogue platform to continue the dialogue with the target user according to the parameters; execute the step of obtaining text information until the dialogue between the dialogue platform and the target user stops.

In a seventh aspect, a computer-readable storage medium storing computer-readable instructions is provided, and a program for man-machine dialogue is stored thereon. When the program for the man-machine dialogue is executed by a processor, the following processing is implemented: During a dialogue, obtain the dialogue data of the target user, and generate dialogue text information based on the dialogue data; provide the dialogue text information to the framework of the configurable parameter extraction function for the purpose of the configurable parameter extraction function The framework extracts the parameters of the dialogue text information based on the pre-configured parameter extraction function, and receives the parameters of the dialogue text information extracted by the framework; continues the dialogue with the target user according to the parameters, and The steps of obtaining the dialogue data of the target user and generating dialogue text information based on the dialogue data are continued until the dialogue with the target user stops.

The above-mentioned human-machine dialogue method, device, computer equipment and computer-readable storage medium utilize a pre-established framework with configurable parameter extraction function to extract parameters from the text information from the dialogue platform, and the specific parameter extraction function of the framework is It can be configured according to requirements before use. The framework integrates a variety of parameter extraction functions and supports the configuration of multiple parameter extraction functions, making it basically unnecessary for developers to re-develop corresponding types of parameter extraction codes when extracting parameters from dialog data. Therefore, the use efficiency of the human-machine dialogue platform can be improved, the use of the dialogue platform is more convenient, and the needs of more scenarios can be met.

It should be understood that the above general description and the following detailed description are only exemplary and cannot limit the application.

Description of the drawings

Fig. 1 is a schematic diagram showing a system architecture of a human-machine dialogue method according to an exemplary embodiment;

Fig. 2 is a flow chart showing a method for man-machine dialogue according to an exemplary embodiment;

FIG. 3 is a flowchart of the steps before step 220, the steps after step 230, and the details of step 250 according to an embodiment corresponding to FIG. 2;

Fig. 4 is a flow chart showing a method for man-machine dialogue according to another exemplary embodiment;

Fig. 5 is a block diagram showing a device for man-machine dialogue according to an exemplary embodiment;

Fig. 6 is an exemplary block diagram showing a computer device implementing the above-mentioned human-machine dialogue method according to an exemplary embodiment;

Fig. 7 shows a computer-readable storage medium for implementing the above-mentioned human-machine dialogue method according to an exemplary embodiment.

Detailed ways

The exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.

In addition, the drawings are only schematic illustrations of the application and are not necessarily drawn to scale. The same reference numerals in the figures denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

This application first provides a method for man-machine dialogue. In the technical solution of the present application, the main form of human-machine dialogue is that the dialogue platform conducts dialogue with humans, and the dialogue platform receives dialogue data fed back by humans and sends corresponding dialogue data to humans based on the dialogue data to conduct dialogues with humans. The dialogue platform may include a variety of modules, models, or algorithms for realizing dialogue with humans, for example, it may include a speech synthesis module, language model, acoustic model, etc. The dialogue platform may conduct text, voice or video voice dialogue with humans. The human-machine dialogue method provided in this application can be executed by a framework with a configurable parameter extraction function. The framework can establish a data transmission channel with the dialogue platform. By configuring the required parameter extraction function for the framework in advance, the dialogue platform can be Corresponding parameter extraction is performed on the sent dialogue text information, and the extracted parameters will be fed back to the dialogue platform, so that the dialogue platform performs better when conducting man-machine conversations with humans. The human-machine dialogue method of this application can be applied to various scenarios, such as financial scenarios. A specific example of application to financial scenarios can be to review whether loans are allowed to users through a dialogue platform, or to obtain information through communication with users. Historical behavior data for financial risk or personal financial evaluation.

The implementation terminal of this application can be any device with computing, processing, and communication functions. The device can be connected to an external device to receive or send data. Specifically, it can be a portable mobile device, such as a smart phone, a tablet computer, a notebook computer, PDA (Personal Digital Assistant), etc., can also be fixed devices, such as computer equipment, field terminals, desktop computers, servers, workstations, etc., or a collection of multiple devices, such as cloud computing physical infrastructure or server clusters . Optionally, the implementation terminal of this application may be a server or a physical infrastructure of cloud computing.

Fig. 1 is a schematic diagram showing a system architecture of a human-machine dialogue method according to an exemplary embodiment. As shown in Figure 1, the system architecture includes a server 110, a desktop computer 120, and a user terminal 130. The desktop computer 120 and the server 110, and the user terminal 130 and the desktop computer 120 are all connected by communication links, so that data can be performed. Receiving and sending. The desktop computer 120 is fixedly provided with a dialogue platform, and the server 110 is fixedly provided with a framework with a configurable parameter extraction function. Therefore, in this embodiment, the server 110 may be the implementation terminal of the application. When the man-machine dialogue method provided by this application is applied to the system architecture shown in FIG. 1, a specific process can be as follows: First, the user uses the user terminal 130 to initiate a conversation with the dialogue platform fixed on the desktop computer 120. The dialogue platform on the computer 120 will receive the voice dialogue data from the user terminal 130, convert the voice dialogue data into dialogue text information, and send the dialogue text information to the server 110; The set frame has been pre-configured with the parameter extraction function, and the parameters in the dialog text information can be quickly extracted using this frame. The server 110 will send the extracted parameters to the dialog platform on the desktop computer 120, and the dialog platform uses the parameters to It can determine how to further dialogue with the user, that is, the dialogue platform can truly understand the meaning of the dialogue data that the user feedbacks last time, so that the man-machine dialogue with the user can be continued.

It is worth mentioning that Fig. 1 is only an embodiment of the present application. Although the implementing terminal in this embodiment is a server, in other embodiments, the implementing terminal may be various terminals or devices as described above; although in this embodiment, a framework with a configurable parameter extraction function and The dialogue platforms are respectively fixed on different terminals, but in other embodiments or specific applications, the framework with the configurable parameter extraction function and the dialogue platform can be set on the same terminal. This application does not make any limitation on this. The scope of protection should not be restricted as a result.

Fig. 2 is a flow chart showing a method for man-machine dialogue according to an exemplary embodiment. At the physical level, the man-machine dialogue method provided by this embodiment can be executed by the server; and at the logical level, the man-machine dialogue method provided by this embodiment is executed by a framework with a configurable parameter extraction function, as shown in Figure 2, including The following steps:

Step 220: After the dialogue platform starts a dialogue with the target user, perform a step of obtaining text information. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform.

The dialogue text information is generated by the dialogue platform according to the dialogue data of the target user and provided to the framework with a configurable parameter extraction function.

The dialogue platform first obtains the dialogue data of the target user, and then generates dialogue text information based on the dialogue data. A parameter is an element or information item recorded in the dialog text information. For example, the parameter can be a keyword in a piece of dialog text information. The dialog data of the target user can be voice data, text data, or audio and video data.

When the dialogue data of the target user is text data, the text data can be directly used as dialogue text information. When the dialogue data of the target user is voice data, the process of generating dialogue text information by the dialogue platform according to the dialogue data may include: converting the dialogue data into text information as the generated dialogue text information. This conversion process can be implemented using models or algorithms such as speech recognition.

Step 230: Extract the parameters of the dialog text information based on the pre-configured parameter extraction function.

In one embodiment, the configurable parameter extraction function of the framework includes one or more of the following: a parameter extraction function of different parameter items corresponding to a plurality of preset extraction functions respectively; corresponding to at least one parameter item The parameter extraction function based on regular expressions is implemented based on a preset configuration format; the parameter extraction function based on external links is used to introduce an external parameter extraction function that corresponds to at least one parameter item Parameter extraction function; additional vocabulary function for extracting other parameters that are semantically similar to the basic extraction result corresponding to at least one extraction function, and the basic extraction result is the parameter with the most identical manifestations among the parameters extracted by the corresponding extraction function .

The parameter item is the name of a specific parameter. For different dialog text information, different parameters can usually be extracted for the same parameter item. The parameter item of each parameter that can be extracted by the framework corresponds to a parameter type, and there can be one or more parameter items corresponding to the same parameter type. The parameters of different parameter items that can be extracted by the extraction function corresponding to each extraction function may belong to the same or different parameter types. For example, the types of parameters that can be extracted by the framework may include: date type, numeric type, string type, address type, and Boolean type, where the numeric type may include integer type and decimal type. For example, corresponding to the extraction of integer parameters in the numeric type, if the numeric parameter item is the pay date, then the basic extraction result corresponding to the extraction function can be XX month XX day, and they all use the same The format is therefore the same in expression form, and because the extracted parameters of this expression form are the most, therefore, XX month XX day is the parameter with the most expression forms of the same. Other parameters similar to the semantics may include: beginning of the month, middle of the month, end of the month, early, mid, late, etc.

Table 1

For example, see Table 1, which respectively show the parameter extraction functions of the parameter items corresponding to the two extraction functions. The two extraction functions are {$birthday} and {$day}, and the corresponding parameter items are the year of birth. Month, day and pay date, the parameter types corresponding to the extracted parameters are date type and integer type respectively. The Chinese parameter name is the Chinese name set by the user, and the English parameter name is the English name of the parameter that is convenient for the internal management of the system. Frame The functions of two extraction functions are integrated internally. Table 1 also shows additional vocabulary. They are similar in semantics to the basic extraction result corresponding to the extraction function {$day}. The contents shown in Table 1 are all configured in Frame.

IDID	参数名parameter name	正则法则Regular rule	输出变量类型Output variable type
11	提取身份证前6位Extract the first 6 digits of the ID card	//d{6}//d{6}	字符串型String type
22	提取手机号码Retrieve mobile phone number	(13\|14\|15\|18)\\d{9}(13\|14\|15\|18)\\d{9}	字符串型String type

Table 2

Regarding the parameter extraction function based on regular expressions, please refer to Table 2. ID is the system number, the parameter name is the name of the regular rule, the regular rule is the regular expression supported by java programming, and the writing method refers to the regular expression writing rules, output The variable type is the data type of the extracted data.

table 3

Please refer to Table 3, which shows the parameter extraction function based on external links, where ID is the system number; the parameter name is the name of the link parameter extraction function; URL is the address where the external link is called; the user's verbal input corresponds to The Json information field is the json field name corresponding to the idiom that needs to extract the parameters; the other input fields are other required information for successfully calling the link, such as user name and password information; the field corresponding to the returned result is the field corresponding to the result returned by the link name.

In one embodiment, the framework further includes a test verification function, which is used to verify the reliability of the parameter extraction function based on regular expressions and/or the parameter extraction function based on external links to ensure that all The parameter extraction function based on regular expressions and/or the parameter extraction function based on external links are available.

Specifically, the test verification function can be implemented by inputting preset dialogue text information marked with the correctly extracted target parameters into the framework, and by pre-configuring the framework with externally-based information corresponding to the target parameters. Link parameter extraction function and regular expression-based parameter extraction function corresponding to the parameter item, and then input the dialog text information into the framework, and use the framework's parameter extraction function based on external links and the regular expression-based parameter extraction function respectively The parameter extraction function extracts the parameters of the dialog text information, and then compares the extracted parameters with the correct extracted target parameters to verify the parameter extraction function based on regular expressions and the parameter extraction function based on external links it's usable or not.

In one embodiment, the types of parameters that can be extracted by the framework include string type or Boolean type, and the configurable parameter extraction function further includes: a supplementary vocabulary corresponding to at least one string type parameter item or Boolean type parameter item Function to extract the parameter corresponding to the parameter item and belonging to the supplementary vocabulary.

In one embodiment, the extraction of the parameters of the dialog text information based on the pre-configured parameter extraction function includes: based on the pre-configured supplementary vocabulary function corresponding to the string-type parameter item, in the dialog text The parameter corresponding to the parameter item and belonging to the supplementary vocabulary is extracted from the information; the parameter is replaced with a standardized parameter corresponding to the parameter as the parameter extracted from the dialogue text information.

In one embodiment, the types of parameters that can be extracted by the framework include a Boolean type, and the configurable parameter extraction function further includes: an intent recognition function corresponding to at least one Boolean parameter item for extracting information related to the parameter item. Parameters with similar semantics.

Please refer to Table 4. The difference between Table 4 and Table 1 is that it shows the parameter extraction function for Boolean and string parameter items. Among them, the parameter item of name can be extracted by the extraction function, and The difference between the function of date type and integer type parameter extraction in Table 1 is that the parameter items of marriage and provident fund can be extracted by means of supplementary vocabulary, and the parameter item of the first 6 digits of the ID card can be expressed through regular expressions. The parameter item of the unit name can be extracted through external links, and the extraction results of the marriage and provident fund parameter items can also be standardized. For example, whether the parameter extracted for the marriage parameter item is not married If you are single, you will use the standardized "unmarried" as the extracted parameter; the parameter item of provident fund can also be extracted by intention recognition, that is, for the parameter item of provident fund, although the dialogue text information does not include the corresponding parameter item The supplementary vocabulary of, but can identify words with similar semantics to the parameter item of provident fund.

Table 4

Step 250: Send the extracted parameters of the dialogue text information to the dialogue platform for the dialogue platform to continue the dialogue with the target user according to the parameters.

After the dialogue platform obtains the parameters, it is equivalent to obtaining the key information of the target user's last feedback, and the dialogue platform can choose an appropriate expression according to the key information to continue the dialogue with the target user.

Step 260: Perform the step of obtaining text information until the dialogue between the dialogue platform and the target user stops.

Unless the dialogue between the dialogue platform and the target user is stopped, the step of obtaining text information, namely step 220, is executed, so that step 220 and subsequent steps are executed in a loop.

FIG. 3 is a flowchart of the steps before step 220, the steps after step 230, and the details of step 250 according to an embodiment corresponding to FIG. 2. In the embodiment shown in FIG. 3, the aforementioned parameter is the second parameter, and the framework may also be configured with a parameter comparison function. As shown in FIG. 3, the following steps may be included:

Step 210: Obtain a first parameter corresponding to the target user provided by the dialogue platform.

The first parameter is extracted by the dialogue platform based on the personal information submitted by the target user.

The framework with the configurable parameter extraction function and the dialogue platform of the present application may be located on the same terminal, or may be located on different terminals. When located in the same terminal, the dialogue platform writes the first parameter corresponding to the target user into the memory or hard disk, and then the framework reads the first parameter from the memory or hard disk to obtain the first parameter. When located at different terminals, the framework can obtain the first parameter from the dialogue platform through the communication link.

Step 240: Based on the pre-configured parameter comparison function, compare the first parameter and the second parameter of the same type to verify the reliability of the second parameter of the target user to obtain The verification result corresponding to the two parameters.

For example, the dialogue platform pre-stores the age of the target user, the age of the target user can be used as the first parameter; then through the dialogue with the target user, the second parameter extracted is also the age of the target user, and the target user obtained twice before and after By comparing the ages of, it can be determined whether the age of the target user extracted from the second parameter is reliable.

Step 250', the extracted second parameter of the dialogue text information is sent to the dialogue platform along with the corresponding verification result, so that the dialogue platform can compare the result with the second parameter and the verification result according to the second parameter and the verification result. The target user continues the conversation.

The parameter comparison function can automatically determine the difference between the user information input by the system itself and the user information extracted in the dialogue, without manual participation in the judgment, reducing labor costs, improving efficiency, and enabling multi-round dialogue platforms to be applied to more complex finances Scene.

In one embodiment, the configurable parameter comparison function of the framework includes: a general comparison function, wherein the comparison mode of the general comparison function includes equal to, greater than, less than, inclusive, and not included; preset multiple parameter comparisons Function, each parameter comparison function corresponds to the parameter comparison function of different parameter items.

As mentioned above, the types of parameters that can be extracted by the framework can include: date, numeric, string, and boolean, where the numeric can also include integer and decimal.

In one embodiment, in the comparison mode of the general comparison function, equal to, greater than, and less than correspond to date and/or numeric parameter types, and the comparison mode of the general comparison function in the comparison mode is equal to, contains, and does not correspond to Contains the parameter type corresponding to the string type and/or boolean type.

table 5

For example, see Table 5, which shows two comparison functions of "equal" and parameter comparison function in the general comparison function. ID is the system code; the comparison parameter name is the English name of the parameter item that records the comparison result; the Chinese name is the Chinese name of the parameter item; the parameter mentioning parameter is the English name of the parameter item mentioned in the framework in the previous embodiment, which is the system passing the parameter framework The extracted parameter item; the input parameter is the name of the known information parameter item in the input system; the preset comparison method is the comparison function of some special parameters provided by the system, in Table 5 it is the {$compareBirthday} function; the comparison method: equal , Refers to whether they are equal. You can also choose other comparison methods such as greater than and less than; whether to allow error: true is the allowable error, false is the allowable error, that is, based on the comparison function of the set error range, there is the allowable error range of the comparison. As shown in the figure, the comparison of the number of employees is allowed to have an error of 10%, and within the error range, they are considered to be consistent; the comparison result: there are 3 kinds of satisfaction, that is, two data are consistent; not satisfied, that is two data Inconsistent; the inability to compare is due to the lack of data between the two, which makes it impossible to compare. Standardized results: The comparison results can be standardized, and correspond to the previous values one-to-one.

In one embodiment, the types of parameters that the framework compares through a configurable parameter comparison function include: numerical type, and the configurable parameter comparison function of the framework further includes a comparison function based on a set error range, wherein, The comparison function based on the set error range is used in conjunction with the equal comparison method. The comparison of the number of employees shown in Table 5 allows an error of 10%, which is the comparison function based on the set error range.

In one embodiment, the types of parameters compared by the framework through a configurable parameter comparison function include: string type, and the configurable parameter comparison function of the framework further includes a pinyin-based comparison function, wherein the The pinyin-based comparison function is used in conjunction with the comparison method of equals.

In one embodiment, based on the pre-configured parameter comparison function, the first parameter and the second parameter of the same type are compared to verify the reliability of the second parameter of the target user To obtain a verification result corresponding to each second parameter, including: comparing the first parameter and the second parameter of the same type based on a pre-configured parameter comparison function to obtain a comparison result; The result is replaced with the corresponding standardized result as the verification result corresponding to each second parameter.

In this embodiment, by replacing the comparison result with the standardized result, the consistency and standardization of the verification result are ensured, and the accuracy of the dialogue is improved.

Table 6

Please refer to Table 6, which shows two comparison functions of "equal" and parameter comparison function in the general comparison function. ID is the system code; the comparison parameter name is the English name of the parameter item that records the comparison result; the Chinese name is the Chinese name of the parameter item; the parameter reference is the English name of the parameter item of the parameter mentioned in the framework in the previous embodiment, which is passed by the system The parameters extracted by the parameter framework; the input parameters are the names of the known information parameter items in the input system; the preset comparison mode provides the system with the comparison function of some special parameters. If the ID number is consistent and compared, the preset function function will have multiple comparison results. In Table 5, it is the {$compareID} function. As shown in the picture. Comparison method: equal means whether it is equal or not. Other comparison methods such as contained (contained) and contained (contained) can also be selected; whether to allow pinyin comparison, that is, the comparison function based on pinyin: true is allowed, false is not allowed. Example: "Li Si" is the system input, and "Li Si" is the parameter value. If the characters are compared, the two are inconsistent. If the pinyin comparison is allowed, they are consistent, that is, the comparison result is satisfactory. Comparison result: There are three general types. In the embodiment of Table 6, only the comparison method of equal (that is, whether it is equal) corresponding to CompareName is shown. If it is preset by the system, the results are diverse. Standardization: The comparison results can be standardized, corresponding to the previous comparison results one by one.

To sum up, according to the man-machine dialogue method provided by the embodiment in FIG. 2, a pre-established framework with a configurable parameter extraction function is used to extract parameters from the text information from the dialogue platform, and the specific parameter extraction function of the framework is It can be configured according to requirements before use. The framework integrates a variety of parameter extraction functions and supports the configuration of multiple parameter extraction functions, making it basically unnecessary for developers to re-develop corresponding types of parameter extraction codes when extracting parameters from dialog data. Therefore, the use efficiency of the human-machine dialogue platform can be improved, the use of the dialogue platform is more convenient, and the needs of more scenarios can be met.

Referring to Figure 4, this application also provides a human-machine dialogue method, which is executed by a dialogue platform and includes:

Step 410: During a dialogue with a target user, obtain dialogue data of the target user, and generate dialogue text information based on the dialogue data.

Step 420: Provide the dialog text information to the framework of the configurable parameter extraction function, so that the framework of the configurable parameter extraction function extracts the parameters of the dialog text information based on the pre-configured parameter extraction function, and Receiving the parameters of the dialog text information extracted by the framework.

Step 430: Continue to have a dialogue with the target user according to the parameters, and continue to perform the steps of obtaining dialogue data of the target user and generating dialogue text information based on the dialogue data, until communication with the target user The conversation stopped.

Steps 410 to 430 correspond to the steps shown in the embodiment in FIG. 2. For specific technical details of steps 410 to 430, please refer to the embodiment shown in FIG. 2, which will not be repeated here.

This application also provides a human-machine dialogue device. The following are device embodiments of this application.

Fig. 5 is a block diagram showing a human-machine dialogue device according to an exemplary embodiment. The human-machine dialogue device includes a framework with a configurable parameter extraction function. As shown in FIG. 5, the device 500 includes:

The obtaining module 510 is configured to perform a step of obtaining text information after the dialogue platform starts a dialogue with the target user. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform, Dialogue text information is generated by the dialogue platform according to the dialogue data of the target user and provided to the framework with configurable parameter extraction function;

The parameter extraction module 520 is configured to extract the parameters of the dialog text information based on a pre-configured parameter extraction function;

The sending module 530 is configured to send the extracted parameters of the dialogue text information to the dialogue platform, so that the dialogue platform can continue the dialogue with the target user according to the parameters;

The execution module 540 is configured to execute the step of obtaining text information until the dialogue between the dialogue platform and the target user is stopped.

In one embodiment, the parameter is a second parameter, and the framework may also be configured with a parameter comparison function;

The obtaining module is further configured to obtain a first parameter corresponding to the target user provided by the dialogue platform before performing the step of obtaining text information, and the first parameter is based on the personal information submitted by the target user by the dialogue platform. Extracted

The parameter extraction module is further configured to, after extracting the parameters of the dialog text information based on the pre-configured parameter extraction function, and then, based on the pre-configured parameter comparison function, compare the same type of the first parameter and the Comparing the second parameters to verify the reliability of the second parameters of the target user, and obtain a verification result corresponding to each second parameter;

The sending module is further configured to send the extracted second parameter of the dialog text information together with the corresponding verification result to the dialog platform, so that the dialog platform can use the second parameter and the calibration result according to the second parameter. The result of the test is to continue the dialogue with the target user.

According to another aspect of the present application, a computer device is also provided, which executes all or part of the steps of any one of the above-mentioned man-machine dialogue methods. The computer equipment includes:

At least one processor; and

A memory communicatively connected with the at least one processor; wherein,

The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute as shown in any of the foregoing exemplary embodiments. Man-machine dialogue method.

Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method, or a program product. Therefore, each aspect of the present application can be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as "Circuit", "Module" or "System".

The computer device 600 according to this embodiment of the present application will be described below with reference to FIG. 6. The computer device 600 shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present application.

As shown in FIG. 6, the computer device 600 is represented in the form of a general-purpose computing device. The components of the computer device 600 may include, but are not limited to: the aforementioned at least one processing unit 610, the aforementioned at least one storage unit 620, and a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610). Wherein, the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the various exemplary methods described in the above-mentioned "Embodiment Method" section of this specification. Steps of implementation. The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 621 and/or a cache storage unit 622, and may further include a read-only storage unit (ROM) 623. The storage unit 620 may also include a program/utility tool 624 having a set of (at least one) program module 625. Such program module 625 includes but is not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples or some combination may include the implementation of a network environment. The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any bus structure among multiple bus structures. bus. The computer device 600 can also communicate with one or more external devices 800 (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable a user to interact with the computer device 600, and/or communicate with Any device (such as a router, a modem, etc.) that enables the computer device 600 to communicate with one or more other computer devices. This communication can be performed through an input/output (I/O) interface 650. In addition, the computer device 600 may also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 660. As shown in the figure, the network adapter 660 communicates with other modules of the computer device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and/or software modules can be used in conjunction with the computer device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc. Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computer device (which may be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiment of the present application.

According to another aspect of the present application, there is also provided a computer-readable storage medium on which is stored a program product capable of realizing the above-mentioned method of this specification. The computer-readable storage medium may be non-volatile or easily accessible. Loss of sex. In some possible implementation manners, each aspect of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to make the The terminal device executes the steps according to various exemplary embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

Referring to FIG. 7, a program product 700 for implementing the above method according to an embodiment of the present application is described. It can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be stored in a terminal device, For example, running on a personal computer. However, the program product of this application is not limited to this. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

The program product can use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Type programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than a readable storage medium, and the readable medium may send, propagate, or transmit a program for use by or in combination with the instruction execution system, apparatus, or device. The program code contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing. The program code used to perform the operations of this application can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming languages. Programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computer equipment, partly on the user's equipment, executed as an independent software package, partly on the user's computer equipment and partly executed on the remote computer equipment, or entirely on the remote computer equipment or server. Executed on. In the case of remote computer equipment, the remote computer equipment can be connected to the user’s computer equipment through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer equipment (for example, using Internet service providers). Business to connect via the Internet).

In addition, the above-mentioned drawings are merely schematic illustrations of the processing included in the method according to the exemplary embodiments of the present application, and are not intended for limitation. It is easy to understand that the processing shown in the above drawings does not indicate or limit the time sequence of these processings. In addition, it is easy to understand that these processes can be executed synchronously or asynchronously in multiple modules, for example.

It should be understood that the present application is not limited to the precise structure that has been described above and shown in the drawings, and various modifications and changes can be performed without departing from its scope. The scope of the application is only limited by the appended claims.

Claims

A human-machine dialogue method, the method is executed by a framework with a configurable parameter extraction function, and the method includes:

After the dialogue platform starts a dialogue with the target user, a step of obtaining text information is performed. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform, and the dialogue text information is determined by the dialogue The platform generates and provides the framework with the configurable parameter extraction function according to the dialogue data of the target user;

Extract the parameters of the dialogue text information based on the pre-configured parameter extraction function;

Sending the extracted parameters of the dialogue text information to the dialogue platform for the dialogue platform to continue the dialogue with the target user according to the parameters;

The step of obtaining text information is performed until the dialogue between the dialogue platform and the target user is stopped.
The method according to claim 1, wherein the configurable parameter extraction function of the framework includes one or more of the following:

Parameter extraction function of different parameter items corresponding to multiple preset extraction functions respectively;

A parameter extraction function based on a regular expression corresponding to at least one parameter item, the regular expression being implemented based on a preset configuration format;

The parameter extraction function based on the external link is used to introduce the external parameter extraction function, and the external parameter extraction function corresponds to the parameter extraction function of at least one parameter item;

The additional vocabulary function is used to extract other parameters that are semantically similar to the basic extraction result corresponding to at least one extraction function, and the basic extraction result is the parameter with the most identical manifestations among the parameters extracted by the corresponding extraction function.
The method according to claim 1 or 2, wherein the framework further comprises a test verification function, the test verification function is used to verify the reliability of the parameter extraction function based on regular expressions and/or the parameter extraction function based on external links The performance is verified to ensure that the parameter extraction function based on regular expressions and/or the parameter extraction function based on external links is available.
The method according to claim 1 or 2, wherein the types of parameters that can be extracted by the framework include string type or Boolean type, and the configurable parameter extraction function further includes: corresponding to at least one string type parameter item or The supplementary vocabulary function of the Boolean parameter item is used to extract the parameter corresponding to the parameter item and belonging to the supplementary vocabulary.
The method according to claim 4, wherein the type of the parameters that can be extracted by the framework includes a Boolean type, and the configurable parameter extraction function further includes:

The intent recognition function corresponding to at least one Boolean parameter item is used to extract a parameter that is semantically similar to the parameter item.
The method according to claim 1 or 2, wherein the parameter is a second parameter, and the framework can also be configured with a parameter comparison function;

Before performing the step of obtaining text information, the method further includes obtaining a first parameter corresponding to the target user provided by the dialogue platform, the first parameter being extracted by the dialogue platform based on the personal information submitted by the target user ；

After the parameters of the dialog text information are extracted based on the pre-configured parameter extraction function, the method further includes, based on the pre-configured parameter comparison function, comparing the first parameter and the second parameter of the same type. Making a comparison to verify the reliability of the second parameter of the target user to obtain a verification result corresponding to each second parameter;

The sending the extracted parameters of the dialog text information to the dialog platform for the dialog platform to continue the dialog with the target user according to the parameters includes: The two parameters are sent to the dialogue platform together with the corresponding verification result, so that the dialogue platform can continue the dialogue with the target user according to the second parameter and the verification result.
A human-machine dialogue method, the method is executed by a dialogue platform, and the method includes:

During a dialogue with a target user, obtain dialogue data of the target user, and generate dialogue text information based on the dialogue data;

The dialog text information is provided to the framework of the configurable parameter extraction function, so that the framework of the configurable parameter extraction function extracts the parameters of the dialog text information based on the pre-configured parameter extraction function, and receives the The parameters of the dialogue text information obtained by frame extraction;

Continue the dialogue with the target user according to the parameters, and continue to execute the step of obtaining dialogue data of the target user and generating dialogue text information based on the dialogue data, until the dialogue with the target user stops .
A human-machine dialogue device, the device includes a framework with a configurable parameter extraction function, and the device includes:

The obtaining module is configured to execute the step of obtaining text information after the dialogue platform starts a dialogue with the target user. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform. The text information is generated by the dialogue platform according to the dialogue data of the target user and provided to the framework with configurable parameter extraction function;

The parameter extraction module is configured to extract the parameters of the dialog text information based on a pre-configured parameter extraction function;

A sending module, configured to send the extracted parameters of the dialogue text information to the dialogue platform, so that the dialogue platform can continue the dialogue with the target user according to the parameters;

The execution module is configured to execute the step of obtaining text information until the dialogue between the dialogue platform and the target user stops.
A computer device includes a memory and a processor, and computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor executes:

After the dialogue platform starts a dialogue with the target user, a step of obtaining text information is performed. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform, and the dialogue text information is determined by the dialogue The platform generates and provides to the framework with configurable parameter extraction function according to the dialogue data of the target user;

Extract the parameters of the dialogue text information based on the pre-configured parameter extraction function;

Sending the extracted parameters of the dialogue text information to the dialogue platform for the dialogue platform to continue the dialogue with the target user according to the parameters;

The step of obtaining text information is performed until the dialogue between the dialogue platform and the target user is stopped.
9. The computer device according to claim 9, wherein the frame-configurable parameter extraction function includes one or more of the following:

Parameter extraction function of different parameter items corresponding to multiple preset extraction functions respectively;

A parameter extraction function based on a regular expression corresponding to at least one parameter item, the regular expression being implemented based on a preset configuration format;

The parameter extraction function based on the external link is used to introduce the external parameter extraction function, and the external parameter extraction function corresponds to the parameter extraction function of at least one parameter item;

The additional vocabulary function is used to extract other parameters that are semantically similar to the basic extraction result corresponding to at least one extraction function, and the basic extraction result is the parameter with the most identical manifestations among the parameters extracted by the corresponding extraction function.
The computer device according to claim 9 or 10, wherein the framework further comprises a test verification function, the test verification function is used to perform the function of parameter extraction based on regular expressions and/or parameter extraction based on external links The reliability is verified to ensure that the parameter extraction function based on regular expressions and/or the parameter extraction function based on external links is available.
The computer device according to claim 9 or 10, wherein the types of parameters that can be extracted by the framework include string type or Boolean type, and the configurable parameter extraction function further includes: corresponding to at least one string type parameter item Or the supplementary vocabulary function of the Boolean parameter item, used to extract the parameter corresponding to the parameter item and belonging to the supplementary vocabulary.
The computer device according to claim 12, wherein the type of the parameters that can be extracted by the framework includes a Boolean type, and the configurable parameter extraction function further includes:

The intent recognition function corresponding to at least one Boolean parameter item is used to extract a parameter that is semantically similar to the parameter item.
The computer device according to claim 9 or 10, wherein the parameter is a second parameter, and the framework can also be configured with a parameter comparison function;

Before performing the step of obtaining text information, when the computer-readable instructions are executed by the processor, the processor also executes: obtaining the first parameter corresponding to the target user provided by the dialogue platform, the first parameter Extracted by the dialogue platform based on the personal information submitted by the target user;

After the parameters of the dialog text information are extracted based on the pre-configured parameter extraction function, when the computer-readable instructions are executed by the processor, the processor also executes: a comparison function based on the pre-configured parameters , Comparing the first parameter and the second parameter of the same type to verify the reliability of the second parameter of the target user to obtain a verification result corresponding to each second parameter;

The sending the extracted parameters of the dialog text information to the dialog platform for the dialog platform to continue the dialog with the target user according to the parameters includes: The two parameters and the corresponding verification result are sent to the dialogue platform, so that the dialogue platform can continue the dialogue with the target user according to the second parameter and the verification result.
A computer device includes a memory and a processor, and computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor executes:

During a dialogue with a target user, obtain dialogue data of the target user, and generate dialogue text information based on the dialogue data;

The dialog text information is provided to the framework of the configurable parameter extraction function, so that the framework of the configurable parameter extraction function extracts the parameters of the dialog text information based on the pre-configured parameter extraction function, and receives the The parameters of the dialogue text information obtained by frame extraction;

Continue the dialogue with the target user according to the parameters, and continue to execute the step of obtaining dialogue data of the target user and generating dialogue text information based on the dialogue data, until the dialogue with the target user stops .
A computer-readable storage medium storing computer-readable instructions, which when executed by one or more processors, cause one or more processors to execute:

After the dialogue platform starts a dialogue with the target user, a step of obtaining text information is performed. The step of obtaining text information includes obtaining the dialogue text information of the target user provided by the dialogue platform, and the dialogue text information is determined by the dialogue The platform generates and provides to the framework with configurable parameter extraction function according to the dialogue data of the target user;

Extract the parameters of the dialogue text information based on the pre-configured parameter extraction function;

Sending the extracted parameters of the dialogue text information to the dialogue platform for the dialogue platform to continue the dialogue with the target user according to the parameters;

The step of obtaining text information is performed until the dialogue between the dialogue platform and the target user is stopped.
The computer-readable storage medium according to claim 16, wherein the framework configurable parameter extraction function includes one or more of the following:

Parameter extraction function of different parameter items corresponding to multiple preset extraction functions respectively;

A parameter extraction function based on a regular expression corresponding to at least one parameter item, the regular expression being implemented based on a preset configuration format;

The parameter extraction function based on the external link is used to introduce the external parameter extraction function, and the external parameter extraction function corresponds to the parameter extraction function of at least one parameter item;

The additional vocabulary function is used to extract other parameters whose semantics are similar to the basic extraction result corresponding to at least one extraction function, and the basic extraction result is the parameter with the most identical manifestations among the parameters extracted by the corresponding extraction function.
The computer-readable storage medium according to claim 16 or 17, wherein the framework further includes a test verification function, which is used to extract parameters based on regular expressions and/or parameters based on external links. The reliability of the extraction function is verified to ensure that the parameter extraction function based on regular expressions and/or the parameter extraction function based on external links is available.
The computer-readable storage medium according to claim 16 or 17, wherein the type of the parameters that can be extracted by the framework includes a string type or a Boolean type, and the configurable parameter extraction function further includes: corresponding to at least one string The supplementary vocabulary function of the type parameter item or the Boolean parameter item is used to extract the parameter corresponding to the parameter item and belonging to the supplementary vocabulary.
The computer-readable storage medium according to claim 19, wherein the type of the parameters that can be extracted by the framework includes a Boolean type, and the configurable parameter extraction function further includes:

The intent recognition function corresponding to at least one Boolean parameter item is used to extract a parameter that is semantically similar to the parameter item.
The computer-readable storage medium according to claim 16 or 17, wherein the parameter is a second parameter, and the framework can also be configured with a parameter comparison function;

Before performing the step of obtaining text information, when the computer-readable instructions are executed by one or more processors, the one or more processors also execute: obtain the first parameter corresponding to the target user provided by the dialogue platform, so The first parameter is extracted by the dialogue platform based on the personal information submitted by the target user;

After the parameters of the dialog text information are extracted based on the pre-configured parameter extraction function, when the computer-readable instructions are executed by one or more processors, the one or more processors also execute: The parameter comparison function of, compares the first parameter and the second parameter of the same type to verify the reliability of the second parameter of the target user, and obtain the verification corresponding to each second parameter result;

The sending the extracted parameters of the dialog text information to the dialog platform for the dialog platform to continue the dialog with the target user according to the parameters includes: The two parameters are sent to the dialogue platform together with the corresponding verification result, so that the dialogue platform can continue the dialogue with the target user according to the second parameter and the verification result.
A computer-readable storage medium storing computer-readable instructions, which when executed by one or more processors, cause one or more processors to execute:

During a dialogue with a target user, obtain dialogue data of the target user, and generate dialogue text information based on the dialogue data;

The dialog text information is provided to the framework of the configurable parameter extraction function, so that the framework of the configurable parameter extraction function extracts the parameters of the dialog text information based on the pre-configured parameter extraction function, and receives the The parameters of the dialogue text information obtained by frame extraction;

Continue the dialogue with the target user according to the parameters, and continue to execute the step of obtaining dialogue data of the target user and generating dialogue text information based on the dialogue data, until the dialogue with the target user stops .