Methods and related devices for cultivating expressive abilities based on interactive information

Abstract

This application provides a method and related apparatus for cultivating expressive abilities based on interactive information. The method includes: invoking a human-computer dialogue engine that assigns human-computer dialogue logic according to an interactive script of a target story for interaction; determining whether to obtain a first ratio and a first number of complex-type input statements entered by the user before the current interaction node by judging the type of the user's first input statement in the interaction process data and the type of the current interaction node; if the first ratio is greater than a preset ratio and the first number is greater than a preset number, then determining the next story node to jump to; if the first ratio is less than a preset ratio, then outputting a machine-guided statement to obtain the user's second input statement; if the score of expressive ability determined based on the second input statement exceeds a preset score, then determining the next story node to jump to. This application's scheme for determining expressive ability cultivation based on interactive process data improves the accuracy and intelligence of the cultivation process.

Description

Technical Field

[0001] This application belongs to the field of general data processing technology in the Internet industry, and specifically relates to a method and related apparatus for cultivating expressive ability based on interactive information. Background Art

[0002] Interactive stories, with their unique storytelling presentation, are gaining popularity among users, especially younger ones. They often extend reading time while maintaining high levels of focus, which allows for faster absorption of new knowledge and easier learning of new skills, such as the ability to accurately express one's thoughts in both life and work. However, existing interactive stories are mostly used for entertainment, merely presenting the plot, making their function too simplistic. Summary of the Invention

[0003] This application provides a method and related apparatus for cultivating expressive ability based on interactive information. The method determines the scheme for cultivating expressive ability through interactive process data, thereby prompting the user's expressive ability. While accurately determining the user's expressive ability, it improves the accuracy and rationality of the cultivation process.

[0004] Firstly, this application provides a method for cultivating expressive abilities based on interactive information, applied to a server of a cultivation system. The cultivation system includes the server and a terminal device where a user logs in to a registered interactive story account. The server and the terminal device are connected via a network. The interactive story associated with the interactive story account includes a target story. The method includes:

[0005] Establish a call connection with the terminal device;

[0006] The target human-computer dialogue engine is invoked to interact with the user through the call connection. The human-computer dialogue logic of the target human-computer dialogue engine is given by the interaction script of the target story. The interaction script includes multiple interaction nodes. Each interaction node includes a machine response strategy and user response content. The machine response strategy includes outputting machine statements, and the user response content corresponds to the expected player input statement.

[0007] Obtain the user's first input statement from the process data of the interaction;

[0008] If the first input statement is a simple type input statement, but the current interaction node is a first type interaction node, then obtain the first proportion of the number of second type interaction nodes to the total number of the plurality of interaction nodes, and obtain the first number of complex type input statements entered by the user before the current interaction node. The first type interaction node represents the interaction node whose user response content is a complex type input statement, and the second type interaction node represents the interaction node whose user response content is a simple type input statement.

[0009] If the first ratio is greater than the preset ratio and the first quantity is greater than the preset quantity, then the next story node to jump to is determined based on the user response content of the current interaction node and the first input statement.

[0010] If the first ratio is less than the preset ratio, the first machine guidance statement in the current interaction node is output. The first machine guidance statement includes a guidance statement that guides the user to input a preset semantic.

[0011] Collect the second input statement from the user regarding the guidance statement for the first machine;

[0012] The user's expressive ability is scored based on the second input statement;

[0013] If the user's expressive ability score exceeds the preset score, then the next story node to jump to is determined based on the user's response content at the current interaction node and the second input statement.

[0014] Secondly, this application provides an apparatus for cultivating expressive ability based on interactive information, comprising:

[0015] A creation unit is used to establish a call connection with a terminal device, which is a device for users to log in to their registered interactive story accounts. The terminal device is located within a cultivation system, which includes a server. The server and the terminal device are connected via a network. The interactive stories associated with the interactive story account include target stories.

[0016] The calling unit is used to call the target human-computer dialogue engine to interact with the user through the call connection. The human-computer dialogue logic of the target human-computer dialogue engine is given by the interaction script of the target story. The interaction script includes multiple interaction nodes. Each interaction node includes a machine response strategy and user response content. The machine response strategy includes outputting machine statements, and the user response content corresponds to the expected player input statement.

[0017] The first acquisition unit is used to acquire the user's first input statement in the process data of the interaction;

[0018] The second acquisition unit is configured to, if the first input statement is a simple type input statement but the current interaction node is a first type interaction node, acquire the first proportion of the number of second type interaction nodes to the total number of the plurality of interaction nodes, and acquire the first number of complex type input statements entered by the user before the current interaction node, wherein the first type interaction node represents the interaction node whose user response content is a complex type input statement, and the second type interaction node represents the interaction node whose user response content is a simple type input statement;

[0019] The first determining unit is configured to determine the next story node to jump to based on the user response content of the current interaction node and the first input statement if the first ratio is greater than a preset ratio and the first quantity is greater than a preset quantity.

[0020] The output unit is configured to output a first machine guidance statement in the current interactive node if the first ratio is less than a preset ratio. The first machine guidance statement includes a guidance statement that guides the user to input a preset semantic.

[0021] The acquisition unit is used to acquire the second input statement from the user in response to the guidance statement of the first machine;

[0022] The second determining unit is used to determine a score of the user's expressive ability based on the second input statement;

[0023] The third determining unit is used to determine the next story node to jump to based on the user's response content at the current interaction node and the second input statement if the user's expression ability score exceeds a preset score.

[0024] Thirdly, this application provides an electronic device, including: one or more processors;

[0025] One or more memories are used to store programs.

[0026] The one or more memories and the program are configured such that the one or more processors control the electronic device to execute instructions for steps as described in any of the methods of the first aspect of the embodiments of this application.

[0027] Fourthly, this application provides a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any of the methods of the first aspect of the embodiments of this application.

[0028] Fifthly, this application provides a computer program operable to cause a computer to perform some or all of the steps described in any of the methods of the first aspect of the embodiments of this application. The computer program may be a software installation package.

[0029] The beneficial effects of the technical solutions provided in some embodiments of this application include at least the following:

[0030] As can be seen, in this embodiment, a call connection is established with the user's terminal device, and a target human-computer dialogue engine, which is given interpersonal dialogue logic according to the interactive script of the target story, interacts with the user through the call connection. The interactive script includes multiple interactive nodes, and each interactive node includes a machine response strategy and user response content. The machine response strategy includes outputting machine statements, and the user response content corresponds to the expected player input statement. The system obtains the user's first input statement in the interaction process data and determines whether the first input statement is a simple type of input statement. If the first input statement is a simple type of input statement, but the current interactive node is a first type of interactive node, the system obtains the first proportion of the number of second type interactive nodes to the total number of multiple interactive nodes, and obtains the complex type of input statements entered by the user before the current interactive node. The system uses a first quantity and a first type of interaction node to represent interaction nodes where the user's response content is a complex input statement, and a second type of interaction node to represent interaction nodes where the user's response content is a simple input statement. If the first ratio is greater than a preset ratio and the first quantity is greater than a preset quantity, then the next story node to jump to is determined based on the user's response content and the first input statement of the current interaction node. If the first ratio is less than a preset ratio, then the first machine-guided statement in the current interaction node is output. The first machine-guided statement includes a guiding statement that guides the user to input a preset semantic. The system also collects the user's second input statement in response to the first machine-guided statement. If the user's expression ability score determined based on the second input statement exceeds a preset score, then the next story node to jump to is determined based on the user's response content and the second input statement of the current interaction node. By acquiring user data during the interaction process, the system determines a plan to cultivate expression ability, provides targeted cultivation plans for different users, improves the intelligence and accuracy of the cultivation process, and enables users to quickly improve their expression ability during reading. Attached Figure Description

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0032] Figure 1 This is a schematic diagram of the structure of a server provided in an embodiment of this application;

[0033] Figure 2 This is a schematic diagram of a cultivation system provided in an embodiment of this application;

[0034] Figure 3 This is a flowchart illustrating a method for cultivating expressive ability based on interactive information, as provided in an embodiment of this application.

[0035] Figure 4 This is a block diagram of the functional units of a device for cultivating expressive ability based on interactive information, provided in an embodiment of this application. Detailed Implementation

[0036] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0037] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0038] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0039] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of a server provided in an embodiment of this application. For example... Figure 1As shown, the server includes a processor 120, a memory 130, a communication module 140, and a program 131. The number of processors 120 can be set according to actual needs. The processors 120 are connected to the memory 130 and the communication module 140 through an internal communication bus.

[0040] There may be one or more programs 131, and no specific limitation is made here. Program 131 is stored in the memory 130 and configured to be executed by the processor 120. Program 131 includes instructions for performing any step in the method embodiments described below.

[0041] The processor 120 may be, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor 120 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit may be a communication module 140, a transceiver, a transceiver circuit, etc., and the storage unit may be a memory 130.

[0042] The memory 130 can be volatile memory or non-volatile memory, or may include both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0043] To better understand the technical solutions of the embodiments of this application, the cultivation systems that may be involved in the embodiments of this application will be introduced first.

[0044] Please see Figure 2 , Figure 2 This is a schematic diagram of a culture system provided in an embodiment of this application.

[0045] This evaluation service system includes at least one server and multiple terminal devices. Each of the terminal devices is network-connected to the server, enabling each terminal device to interact with the server via the network. Figure 2 As shown, it can specifically include terminal device a, terminal device b, ..., terminal device n.

[0046] Each of these multiple terminal devices can be a smartphone, smartwatch, tablet, laptop, desktop computer, wearable device, head-mounted device, in-vehicle terminal, etc., and the specific type of terminal device is not limited here. It should be understood that, for example... Figure 2Each terminal device in the cultivation system shown can have an application (i.e., an application client) installed. When the application client runs on each terminal device, it can interact with the aforementioned... Figure 2 The servers shown interact with each other.

[0047] Please see Figure 3 , Figure 3 This is a flowchart illustrating a method for cultivating expressive ability based on interactive information, provided in an embodiment of this application. The method for cultivating expressive ability based on interactive information, as described in this application, will now be explained in detail with reference to the accompanying drawings. Figure 3 As shown, a method for cultivating expressive abilities based on interactive information is applied to a server of a cultivation system. The cultivation system includes the server and a terminal device where a user logs in to a registered interactive story account. The server and the terminal device are connected via a network. The interactive story associated with the interactive story account includes a target story. The method includes the following steps:

[0048] Step 301: Establish a call connection with the terminal device.

[0049] The system's server and the user's terminal device are connected via a network. The user requests to establish a call with the server through the terminal device, and the server establishes a call connection with the user's terminal device after receiving the request message.

[0050] Step 302: Invoke the target human-computer dialogue engine to interact with the user through the call connection.

[0051] The target human-computer dialogue engine's dialogue logic is assigned through the interactive script of the target story. This interactive script includes multiple interaction nodes, each comprising a machine response strategy and user response content. The machine response strategy includes outputting machine statements, and the user response content corresponds to the expected player input statements. Specifically, after the server determines the target story to be read by the user, it invokes the target human-computer dialogue engine, whose dialogue logic is assigned through the interactive script of the target story, to interact with the user and obtain data on the interaction process. This data supports the subsequent determination of a strategy to cultivate expressive abilities.

[0052] Step 303: Obtain the user's first input statement from the interaction process data.

[0053] In the process of interacting with the user through a call connection using the target human-computer dialogue engine, the user's terminal device generates messages based on the user's input commands and sends them to the server. The server obtains the user's first input statement from the interaction process data, thereby providing data support for subsequently determining the strategy for cultivating expressive abilities.

[0054] Step 304: If the first input statement is a simple type of input statement, but the current interaction node is a first type of interaction node, then obtain the first proportion of the number of second type of interaction nodes to the total number of the plurality of interaction nodes, and obtain the first number of complex type input statements entered by the user before the current interaction node.

[0055] The interaction nodes are categorized into two types: Type 1 and Type 2. Type 2. Type 2. Type 3. Type 4. Type 5. Type 6. Type 7. Type 8. Type 9. Type 1. Type 2. Type 3. Type 4. Type 5. Type 6 ... Input statements are categorized into simple and complex types. A simple input statement is one where the total number of characters is less than the preset character count, or where the ratio of repeated characters to the total character count is greater than the preset ratio. A complex input statement is one where the total number of characters is greater than or equal to the preset character count, and the ratio of repeated characters to the total character count is less than or equal to the preset ratio. For example, if the preset character count is 3 and the preset ratio is 1 / 2, and the first input statement is "I want it," then the first input statement has 4 characters and a ratio of 0. Since the preset character count is 3 and the preset ratio is 1 / 2, the first input statement has more characters than the preset character count, but its ratio is less than the preset ratio; therefore, this first input statement is a complex type. If the first input statement is "I...I I," then the first input statement has 3 characters and a ratio of 1. The first input statement has the same character count as the preset character count, but its ratio is greater than the preset ratio; therefore, this first input statement is a simple type.

[0056] In one possible example, the specific content of simple and complex input statements can be pre-defined. For instance, the statement "OK" can be pre-defined as a simple input statement, and the statement "I want this" as a complex input statement. If the first received input statement is "OK," this first input statement is the same as the pre-defined simple input statement, and therefore it is determined to be a simple input statement. It is understood that the content and number of simple input statements can be set according to actual needs, and are not limited here; similarly, the content and number of complex input statements can be set according to actual needs, and are not limited here.

[0057] Step 305: If the first ratio is greater than the preset ratio and the first quantity is greater than the preset quantity, then determine the next story node to jump to based on the user response content of the current interaction node and the first input statement.

[0058] If the first ratio is greater than the preset ratio and the first quantity is greater than the preset quantity, that is, up to the current interaction node, the proportion of the number of the second type of interaction nodes set for the user to the total number of interaction nodes in the target story is greater than the preset ratio, and the first quantity of complex input statements entered by the user before the current interaction node is greater than the preset quantity, that is, the user has already entered the preset quantity of complex input statements, then the next story node to jump to can be determined based on the user response content of the current interaction node and the first input statement, so as to avoid the user entering too many complex input statements and thus ensure the user's enthusiasm.

[0059] Step 306: If the first ratio is less than a preset ratio, then output the first machine guidance statement in the current interaction node. The first machine guidance statement includes guidance statements that guide the user to input preset semantics.

[0060] If, up to the current interaction node, the number of interaction nodes with the second type of user response content set for the user accounts for less than a preset proportion of the total number of interaction nodes required in the target story, then the first machine guidance statement in the current interaction node is output. The first machine guidance statement includes a guidance statement to guide the user to input a complex type of input statement containing preset semantics, thereby improving the user's expressive ability.

[0061] Step 307: Collect the second input statement from the user regarding the guidance statement for the first machine.

[0062] Specifically, after outputting the first machine guidance statement, the system collects the user's second input statement in response to the first machine guidance statement in the current interaction node.

[0063] Step 308: Determine the score of the user's expressive ability based on the second input statement.

[0064] After obtaining the second input statement, the second input statement is parsed, and the user's expressive ability is scored based on the second input statement, providing data support for subsequent steps.

[0065] Step 309: If the user's expressive ability score exceeds the preset score, then determine the next story node to jump to based on the user's response content at the current interaction node and the second input statement.

[0066] Specifically, after obtaining the user's expression ability score, it is determined whether the user's expression ability score exceeds a preset score. If the user's expression ability score exceeds the preset score, the next story node to jump to is determined based on the user's response content of the current interaction node and the second input statement.

[0067] As can be seen in this example, the process data of the interaction determines whether to acquire the first proportion of the second type of interaction nodes and the first number of complex input statements entered by the user before the current interaction node. Then, based on the first proportion and the first number, it determines whether to output the first machine-guided statement to cultivate the user's expressive ability. This improves the intelligence of the cultivation process, makes the determined scheme more accurate and reasonable, and allows users to maintain their enthusiasm for reading while improving their expressive ability.

[0068] In one possible example, if the user's expressive ability score does not exceed a preset score, machine-guided statements are output again to retrieve the user's input and guide their expression, thereby improving their expressive ability. If the user's expressive ability score still does not exceed the preset score after the number of machine-guided statements output exceeds a preset number, the next story node to jump to is determined based on the user's response at the current interaction node and the user's latest input. This prevents users from losing interest in reading and enhances the intelligence of the learning process.

[0069] In one possible example, if the first ratio is greater than a preset ratio but the first quantity is less than a preset quantity, then the next story node to jump to is determined based on the user response content of the current interaction node and the first input statement, and the first machine guidance statement in the current interaction node is output to guide the user to input a guidance statement with preset semantics, thereby improving the intelligence of the training process.

[0070] In one possible example, determining the user's expressive ability score based on the second input statement includes: if the user intent of the second input statement is identified, then determining the user's expressive ability score within a first numerical range; if the user intent matches the expected user intent, then extracting the keywords of the second input statement and the word order information between the keywords, and calculating the matching degree with the user response content of the current interaction node based on the keywords and the word order information; determining a first value corresponding to the matching degree from the first numerical range according to a preset matching relationship, wherein the first value is the user's expressive ability score, and the matching relationship includes the correspondence between different values ​​and different matching degrees within the first numerical range; if the user intent of the second input statement cannot be identified, then obtaining the number of words in the second input statement; determining a corresponding second value from a second numerical range according to the number of words in the second input statement, wherein the second value is the user's expressive ability score, and the maximum value in the second numerical range is less than the minimum value in the first numerical range.

[0071] In a specific example, after obtaining the user's second input statement, if the user's intent is identified—for example, if the second input statement is "I want to eat watermelon"—and parsing the second input statement clearly confirms the user's affirmative intent to eat watermelon, then the user's intent is considered recognizable. If the second input statement is "I...he," and the user's intent cannot be parsed, then the user's intent is considered unrecognizable. If the user's intent is identified, the user's expressive ability score is determined to be within a first numerical range. After determining the user's expressive ability score to be within a first numerical range, if the user intent matches the expected user intent, the keywords and word order information between the keywords in the second input statement are extracted, and the matching degree with the user's response content at the current interaction node is calculated. For example, if the second input statement is "I eat watermelon," the keywords "I," "watermelon," and "eat" are extracted, and the word order information between the keywords is extracted: subject followed by object, object followed by predicate. If the user's response content at the current interaction node includes "I eat watermelon." The user response content is identified as containing the keywords "I," "eat," and "watermelon," with the following word order: subject followed by predicate, and predicate followed by object. The second input statement is matched against the user response content of the current interaction node. The keyword match rate between the second input statement and the user response content is determined to be 100%, and the word order match rate is 33.3%, resulting in a total match rate of 133.3%. Based on the obtained match rate, a first numerical value is determined from a first numerical range, representing the user's expressive ability score. Determining the expressive ability score based on keywords and word order information makes the scoring process faster and more accurate. If the user's intent cannot be identified with the second input statement, the number of characters in the second input statement is obtained. A second numerical value is determined from a second numerical range based on the number of characters in the second input statement, representing the user's expressive ability score. The maximum value in the second numerical range is less than the minimum value in the first numerical range, thus making the scoring more reasonable.

[0072] As can be seen, in this example, the matching degree between the keywords and word order information of the second input statement and the user's response content of the current interaction node is determined, and then the score of the user's expression ability is determined based on the matching degree, thereby improving the accuracy of the determination result.

[0073] In one possible example, obtaining the first proportion of the number of second-type interactive nodes relative to the total number of the plurality of interactive nodes includes: obtaining the user's account information in the interactive story account, the account information including the user's age information and the user's historical rating of expressive ability; determining a reference proportion of the number of second-type interactive nodes relative to the total number of the plurality of interactive nodes based on the age information; determining a corresponding first adjustment value based on the historical rating, wherein the mean of the historical ratings is negatively correlated with the first adjustment value, the first adjustment value being used to adjust the reference proportion; and determining the first proportion based on the first adjustment value and the reference proportion.

[0074] In a specific example, the first ratio is the proportion of the number of second-type interactive nodes to the total number of multiple interactive nodes. For example, if the first ratio is two-thirds, and the target story has 100 nodes, of which 50 are interactive nodes, then the number of second-type interactive nodes is determined based on the first ratio. Therefore, the number of interactive nodes of the second type was determined to be 33. The account information for the interactive story account includes the user's age and historical ratings of their expressive abilities. The specific steps for obtaining the first proportion may include: obtaining the user's account information in the interactive story account; determining the reference proportion of the number of second-type interactive nodes relative to the total number of multiple interactive nodes based on the age information; and thus setting different numbers of nodes that can perform simple interactions for users of different ages. For example, if the obtained age information shows a user is 5 years old, the preset reference proportion for ages 3 to 5 is one-third, so the reference proportion is determined to be one-third. Specifically, the younger the age, the higher the proportion of second-type interactive nodes, i.e., the larger the reference proportion; conversely, the older the age, the lower the proportion of second-type interactive nodes, i.e., the smaller the reference proportion. Determining the reference proportion based on age meets the needs of users of different ages, thereby improving the intelligence of the nurturing process. The first adjustment value is determined based on historical ratings. For example, the average of historical ratings can be calculated, and this average can be used to determine the corresponding first adjustment value. The average ratings in the historical ratings are negatively correlated with the first adjustment value; that is, the larger the average rating, the smaller the corresponding first adjustment value. This reduces the number of interaction nodes of the second type, allowing for more interaction nodes requiring complex input statements to be set for users with high expressive abilities, thereby further improving their expressive abilities and enhancing the intelligence of the training process. The first adjustment value can be positive or negative. After obtaining the first adjustment value, the sum of the first adjustment value and the reference ratio is calculated; this sum is the first ratio.

[0075] As can be seen, in this example, the first ratio is determined based on the age information and historical rating information in the account information, making the determined first ratio more accurate. Then, different numbers of second-type interaction nodes are set for different users, making the cultivation process more intelligent.

[0076] In one possible example, obtaining the first proportion of the number of second-type interactive nodes relative to the total number of the plurality of interactive nodes includes: obtaining the user's account information in the interactive story account, the account information including the user's age information and the user's historical rating of expressive ability; determining a reference proportion of the number of second-type interactive nodes relative to the total number of the plurality of interactive nodes based on the age information; determining a corresponding first adjustment value based on the historical rating, wherein the mean of the historical ratings is negatively correlated with the first adjustment value, and the first adjustment value is used to adjust the reference proportion; determining a second adjustment value based on the number of words in the first input statement, wherein the number of words in the first input statement is positively correlated with the second adjustment value, and the second adjustment value is used to adjust the reference proportion; and determining the first proportion based on the first adjustment value, the second adjustment value, and the reference proportion.

[0077] In a specific example, the user's account information in the interactive story account is obtained, including the user's age and historical ratings of their expressive ability. Based on the age information, a reference ratio is determined for the number of second-type interactive nodes relative to the total number of multiple interactive nodes, thus setting a reasonable number of easily interactive nodes for users of different ages. A first adjustment value is determined based on the historical rating; a second adjustment value is determined based on the number of words in the first input statement. That is, after obtaining the first input statement, the number of words in the first input statement is counted to determine the current user's engagement level. The number of words in the first input statement is positively correlated with the second adjustment value; that is, if the first input statement has fewer words, the user's engagement is considered low, and second-type interactive nodes need to be added; if the first input statement has more words, the user's engagement is considered high, and second-type interactive nodes are reduced. Specifically, different word count ranges can be pre-set, with different word count ranges corresponding to different second adjustment values, thus improving the efficiency of determining the second adjustment value based on the word count range of the first input statement. A first ratio is determined based on the first adjustment value, the second adjustment value, and the reference ratio.

[0078] As can be seen in this example, the number of interaction nodes of the second type among multiple interaction nodes is further determined based on the average historical rating of users and the enthusiasm of user interaction. This improves the rationality of the determination results, ensures that users are in an active state, improves the efficiency of cultivation, and guarantees the interest of reading.

[0079] In one possible example, the user's engagement level can be determined based on the tone and intonation of their initial input, the duration of inactivity before input, and other factors. For instance, a longer inactivity period indicates lower user engagement, necessitating the addition of a second type of interaction node. Therefore, the inactivity period is positively correlated with the adjustment value. The specific method for determining the user's engagement level is not limited here.

[0080] In one possible example, determining the next story node to jump to based on the user response content of the current interaction node and the first input statement includes: extracting keywords from the first input statement; if a target user response content with a similarity higher than a preset similarity is matched from the user response content of the current interaction node based on the keywords of the first input statement, then the corresponding next story node is matched from a preset jump condition database based on the target user response content, wherein the jump condition database includes the correspondence between different user response contents and different story nodes.

[0081] In a specific example, the steps for determining the next story node to jump to based on the user response content of the current interaction node and the first input statement include: obtaining the keywords of the first input statement; matching the target user response content with a similarity higher than a preset similarity from the user response content of the current interaction node based on the keywords of the first input statement, for example: if the user's first input statement is: watermelon, the keyword of the first input statement is extracted as "watermelon". If the current interaction node includes the first user response content: "I eat watermelon" and the second user response content: "I eat banana". Determine that the keywords included in the first user response content are "I", "eat", and "watermelon"; determine that the keywords included in the second user response content are "I", "eat", and "banana". Match the keywords of the first input statement with the keywords of the user response content of the current interaction node. If the first input statement and the first user response content have one identical keyword, divide the number of identical keywords by the total number of keywords in the first user response content to obtain the matching degree. Determine that the matching degree between the first input statement and the first user response content is approximately 33%, and similarly, determine that the matching degree between the first input statement and the second user response content is 0. If the preset similarity is 20%, the next story node corresponding to the first user response is determined as the next story node to jump to. If no target user response with a similarity higher than the preset similarity is found within the user response content of the current interaction node based on the keywords of the first input statement, a prompt message is output to guide the user to re-enter the information, thereby cultivating the user's expressive ability and improving intelligence. If multiple user response contents with a similarity higher than the preset similarity are found within the user response content of the current interaction node based on the keywords of the first input statement, the user response content with the highest similarity is taken as the target response content.

[0082] As can be seen, in this example, the target user response content is determined by the matching degree between the first input statement and the user response content of the current interaction node, and the next story node corresponding to the target user response content is taken as the next story node to jump to. This makes the next story node more in line with the user's expected plot, improves the accuracy of the determination result, and thus increases the user's reading interest.

[0083] In one possible example, after determining the user's expressive ability score based on the second input statement, the method further includes: if the first input statement is a complex type of input statement, then identifying the intent of the first input statement and obtaining an intent recognition result; if the intent recognition result matches the expected intent recognition result, then determining the next story node to jump to based on the user's response content of the current interaction node and the first input statement; if the intent recognition result does not match the expected intent recognition result, then outputting a second machine guidance statement in the current interaction node, the second machine guidance statement including a guidance statement guiding the user to input a preset semantic; collecting a third input statement from the user in response to the second machine guidance statement; if the user's expressive ability score determined based on the third input statement exceeds a preset score, then determining the next story node to jump to based on the user's response content of the current interaction node and the third input statement.

[0084] In a specific example, if the first input statement detected by the user is a complex type, the next story node to jump to can be determined based on the user's response content at the current interaction node and the first input statement. Specifically, after determining that the first input statement is a complex type, the intent of the first input statement is further identified, and the intent recognition result is obtained. If the intent recognition result matches the expected intent recognition result, the next story node to jump to is determined based on the user's response content at the current interaction node and the first input statement, improving the efficiency of the jump and ensuring the user's reading experience. If the intent recognition result does not match the expected intent recognition result, the second machine-guided statement in the current interaction node is output to guide the user to re-enter, and the user's intent for the third input statement in response to the machine-guided statement is collected. If the user intent of the third input statement is identified, the user's expressive ability score is determined to be within a first numerical range, which is a pre-set range of expressive ability scores. After determining the user's expressive ability score within a first numerical range, if the user's intent matches the expected user intent, the keywords and word order information between the keywords in the third input statement are extracted, and the matching degree with the user's response content at the current interaction node is calculated. Based on the obtained matching degree, a first value corresponding to the matching degree is determined from the first numerical range. This first value is the user's expressive ability score. Determining the expressive ability score based on keywords and word order information makes the scoring process faster and the score results more convincing. If the user's intent in the third input statement cannot be identified, the number of words in the third input statement is obtained. Based on the number of words in the third input statement, a second value is determined from a second numerical range. This second value is the user's expressive ability score, and the maximum value in the second numerical range is less than the minimum value in the first numerical range, thus making the score more reasonable. If the user's expressive ability score determined based on the third input statement exceeds a preset score, the next story node to jump to is determined based on the user's response content at the current interaction node and the third input statement.

[0085] As can be seen in this example, when the user's first input statement is a complex type of input statement, the intent of the first input statement can be further judged to determine whether to directly enter the next story node, thereby saving the user's time. If the intent recognition result cannot match the expected intent recognition result, the user is guided to re-enter, which improves the user's expressive ability and enhances the intelligence of the processing.

[0086] In one possible example, after determining the user's expressive ability score based on the second input statement, the method further includes: determining whether the current interaction node is the end node of the target story; if so, outputting a preset machine output statement, the machine output statement being used to suggest that the user share the target story with the user's guardian; obtaining the user's response statement to the machine output statement; if the response statement indicates agreement to share the target story, obtaining the guardian's contact information in the interaction story account; establishing a communication connection with the guardian's terminal device based on the contact information, and sending a summary of the target story to the guardian's terminal device.

[0087] In a specific example, after determining the user's expressive ability score based on the second input statement, if the current interaction node is detected as the end node of the target story, a preset machine output statement is output to the user's terminal device to suggest that the user share the target story with their guardian, thereby increasing interaction between the user and guardian and further improving the user's expressive ability. If the user's response indicates agreement to share the target story, a synopsis of the target story is generated based on the user's understanding of the story's plot, and the guardian's contact information is obtained from the interactive story account. A communication connection is established with the guardian's terminal device based on the contact information, and the synopsis of the target story is sent to the guardian's terminal device.

[0088] As can be seen in this example, by establishing a communication connection with the guardian, the user can share the target story with the guardian, promote communication between the user and the guardian, further improve the user's expressive ability, and enhance the intelligence of the nurturing process.

[0089] This application provides an apparatus for cultivating expressive abilities based on interactive information, which can be an electronic device. Specifically, the apparatus for cultivating expressive abilities based on interactive information provided in this application may include modules corresponding to the respective steps.

[0090] This application embodiment can divide the device for cultivating expressive ability based on interactive information into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. The module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0091] When dividing each function into modules according to its corresponding function, please refer to [link / reference]. Figure 4 , Figure 4This is a functional unit block diagram of a device for cultivating expressive abilities based on interactive information, provided in an embodiment of this application. The device is connected to a terminal device through which a user logs in to a registered interactive story account. The device includes:

[0092] Creation unit 410 is used to establish a call connection with a terminal device, which is a device for users to log in to their registered interactive story accounts. The terminal device is located within a training system, which includes a server. The server and the terminal device are connected via a network. The interactive stories associated with the interactive story account include target stories.

[0093] Calling unit 420 is used to call the target human-computer dialogue engine to interact with the user through the call connection. The human-computer dialogue logic of the target human-computer dialogue engine is given by the interaction script of the target story. The interaction script includes multiple interaction nodes. Each interaction node includes a machine response strategy and user response content. The machine response strategy includes outputting machine statements. The user response content corresponds to the expected player input statement.

[0094] The first acquisition unit 430 is used to acquire the user's first input statement in the process data of the interaction;

[0095] The second acquisition unit 440 is configured to, if the first input statement is a simple type input statement but the current interaction node is a first type interaction node, acquire the first proportion of the number of second type interaction nodes to the total number of the plurality of interaction nodes, and acquire the first number of complex type input statements entered by the user before the current interaction node, wherein the first type interaction node represents the interaction node whose user response content is a complex type input statement, and the second type interaction node represents the interaction node whose user response content is a simple type input statement;

[0096] The first determining unit 450 is used to determine the next story node to jump to based on the user response content of the current interaction node and the first input statement if the first ratio is greater than a preset ratio and the first quantity is greater than a preset quantity.

[0097] The output unit 460 is used to output a first machine guidance statement in the current interactive node if the first ratio is less than a preset ratio. The first machine guidance statement includes a guidance statement that guides the user to input a preset semantic.

[0098] The acquisition unit 470 is used to acquire the second input statement of the user in response to the first machine guidance statement;

[0099] The second determining unit 480 is used to determine a score of the user's expressive ability based on the second input statement;

[0100] The third determining unit 490 is used to determine the next story node to jump to based on the user's response content at the current interaction node and the second input statement if the user's expression ability score exceeds a preset score.

[0101] In one possible example, the second determining unit 480 is further configured to: if the user intent of the second input statement is identified, determine the user's expressive ability score within a first numerical range; and if the user intent matches the expected user intent, extract the keywords of the second input statement and the word order information between the keywords, and calculate the matching degree with the user response content of the current interaction node based on the keywords and the word order information; determine a first value corresponding to the matching degree from the first numerical range according to a preset matching relationship, wherein the first value is the user's expressive ability score, and the matching relationship includes the correspondence between different values ​​and different matching degrees within the first numerical range; and if the user intent of the second input statement cannot be identified, obtain the number of words in the second input statement; and determine a corresponding second value from a second numerical range according to the number of words in the second input statement, wherein the second value is the user's expressive ability score, and the maximum value in the second numerical range is less than the minimum value in the first numerical range.

[0102] In one possible example, the second acquisition unit 440 is further configured to acquire the user's account information in the interactive story account, the account information including the user's age information and the user's historical rating of expressive ability; and to determine a reference ratio based on the age information to the total number of the second type of interactive nodes; and to determine a corresponding first adjustment value based on the historical rating, wherein the mean of the historical ratings is negatively correlated with the first adjustment value, the first adjustment value being used to adjust the reference ratio; and to determine the first ratio based on the first adjustment value and the reference ratio.

[0103] In one possible example, the second acquisition unit 440 is further configured to acquire the user's account information in the interactive story account, the account information including the user's age information and the user's historical rating of expressive ability; and to determine a reference ratio based on the age information to the total number of the second type of interactive nodes; and to determine a corresponding first adjustment value based on the historical rating, wherein the mean of the historical ratings is negatively correlated with the first adjustment value, and the first adjustment value is used to adjust the reference ratio; and to determine a second adjustment value based on the number of words in the first input statement, wherein the number of words in the first input statement is positively correlated with the second adjustment value, and the second adjustment value is used to adjust the reference ratio; and to determine the first ratio based on the first adjustment value, the second adjustment value, and the reference ratio.

[0104] In one possible example, the first determining unit 450 is further configured to extract keywords from the first input statement; and if a target user response content with a similarity higher than a preset similarity is matched from the user response content of the current interaction node based on the keywords of the first input statement, then the corresponding next story node is matched from a preset jump condition database based on the target user response content, wherein the jump condition database includes the correspondence between different user response content and different story nodes.

[0105] In one possible example, the device further includes a recognition unit, configured to: if the first input statement is a complex type of input statement, recognize the intent of the first input statement and obtain an intent recognition result; and if the intent recognition result matches an expected intent recognition result, determine the next story node to jump to based on the user response content of the current interaction node and the first input statement; and if the intent recognition result does not match the expected intent recognition result, output a second machine guidance statement in the current interaction node, the second machine guidance statement including a guidance statement guiding the user to input a preset semantic; and collect a third input statement from the user in response to the second machine guidance statement; and if the user's expressive ability score determined based on the third input statement exceeds a preset score, determine the next story node to jump to based on the user response content of the current interaction node and the third input statement.

[0106] In one possible example, the device further includes a determination unit, which determines whether the current interaction node is the end node of the target story; if so, it outputs a preset machine output statement, which suggests that the user share the target story with the user's guardian; and obtains the user's reply statement to the machine output statement; and if the reply statement indicates agreement to share the target story, it obtains the guardian's contact information in the interaction story account; and establishes a communication connection with the guardian's terminal device based on the contact information, and sends a summary of the target story to the guardian's terminal device.

[0107] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0108] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0109] This application also provides a computer program product, which includes a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments.

[0110] The computer program product may be a software installation package, and the aforementioned computer includes electronic devices.

[0111] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and other division methods may exist in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0113] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0114] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0115] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0116] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.

Claims

1. A method for cultivating expressive ability based on interactive information, characterized in that, A server is used in a cultivation system, the cultivation system including the server and a terminal device for users to log in to a registered interactive story account, the server and the terminal device being connected via a network, the interactive story associated with the interactive story account including a target story, the method including: Establish a call connection with the terminal device; The target human-computer dialogue engine is invoked to interact with the user through the call connection. The human-computer dialogue logic of the target human-computer dialogue engine is given by the interaction script of the target story. The interaction script includes multiple interaction nodes. Each interaction node includes a machine response strategy and user response content. The machine response strategy includes outputting machine statements, and the user response content corresponds to the expected player input statement. Obtain the user's first input statement from the process data of the interaction; If the first input statement is a simple type input statement, but the current interaction node is a first type interaction node, then obtain the first proportion of the number of second type interaction nodes to the total number of the plurality of interaction nodes, and obtain the first number of complex type input statements entered by the user before the current interaction node. The first type interaction node represents the interaction node whose user response content is a complex type input statement, and the second type interaction node represents the interaction node whose user response content is a simple type input statement. If the first ratio is greater than the preset ratio and the first quantity is greater than the preset quantity, then the next story node to jump to is determined based on the user response content of the current interaction node and the first input statement. If the first ratio is less than the preset ratio, the first machine guidance statement in the current interaction node is output. The first machine guidance statement includes a guidance statement that guides the user to input a preset semantic. Collect the second input statement from the user regarding the guidance statement for the first machine; The user's expressive ability is scored based on the second input statement; If the user's expressive ability score exceeds the preset score, then the next story node to jump to is determined based on the user's response content at the current interaction node and the second input statement.

2. The method according to claim 1, characterized in that, The step of determining the score of the user's expressive ability based on the second input statement includes: If the user's intent in the second input statement is identified, then the user's expressive ability score is determined to be within a first numerical range; If the user intent matches the expected user intent, then extract the keywords of the second input statement and the word order information between the keywords, and calculate the matching degree with the user response content of the current interaction node based on the keywords and the word order information. According to the preset matching relationship, a first value corresponding to the matching degree is determined from the first value range. The first value is the score of the user's expressive ability. The matching relationship includes the correspondence between different values ​​and different matching degrees within the first value range. If the user intent of the second input statement cannot be identified, then obtain the number of characters in the second input statement; The second value is determined from the second numerical range based on the number of characters in the second input statement. The second value is a score of the user's expressive ability, and the maximum value in the second numerical range is less than the minimum value in the first numerical range.

3. The method according to claim 1, characterized in that, The first proportion of the number of second-type interactive nodes to the total number of the plurality of interactive nodes includes: Obtain the user's account information in the interactive story account, the account information including the user's age information and the user's historical rating of expression ability; Based on the age information, determine a reference ratio of the number of the second type of interactive nodes to the total number of the multiple interactive nodes; A first adjustment value is determined based on the historical scores, wherein the mean of the scores in the historical scores is negatively correlated with the first adjustment value, and the first adjustment value is used to adjust the reference ratio. The first ratio is determined based on the first adjustment value and the reference ratio.

4. The method according to claim 1, characterized in that, The first proportion of the number of second-type interactive nodes to the total number of the plurality of interactive nodes includes: Obtain the user's account information in the interactive story account, the account information including the user's age information and the user's historical rating of expression ability; Based on the age information, determine a reference ratio of the number of the second type of interactive nodes to the total number of the multiple interactive nodes; A first adjustment value is determined based on the historical scores, wherein the mean of the scores in the historical scores is negatively correlated with the first adjustment value, and the first adjustment value is used to adjust the reference ratio. A second adjustment value is determined based on the number of characters in the first input statement. The number of characters in the first input statement is positively correlated with the second adjustment value. The second adjustment value is used to adjust the reference ratio. The first ratio is determined based on the first adjustment value, the second adjustment value, and the reference ratio.

5. The method according to any one of claims 1-4, characterized in that, The step of determining the next story node to jump to based on the user response content of the current interaction node and the first input statement includes: Extract the keywords from the first input statement; If a target user response with a similarity higher than a preset similarity is matched from the user response content of the current interaction node based on the keywords of the first input statement, then the corresponding next story node is matched from a preset jump condition database based on the target user response content. The jump condition database includes the correspondence between different user response contents and different story nodes.

6. The method according to any one of claims 1-4, characterized in that, After determining the user's expressive ability score based on the second input statement, the method further includes: If the first input statement is a complex type of input statement, then the intent of the first input statement is identified, and the intent identification result is obtained; If the intent recognition result matches the expected intent recognition result, then the next story node to jump to is determined based on the user response content of the current interaction node and the first input statement; If the intent recognition result does not match the expected intent recognition result, the second machine guidance statement in the current interaction node is output. The second machine guidance statement includes a guidance statement that guides the user to input a preset semantic. Collect the third input statement from the user regarding the boot statement for the second machine; If the user's expressive ability score determined based on the third input statement exceeds the preset score, then the next story node to jump to is determined based on the user's response content at the current interaction node and the third input statement.

7. The method according to any one of claims 1-4, characterized in that, After determining the user's expressive ability score based on the second input statement, the method further includes: Determine whether the current interaction node is the end node of the target story; If so, a preset machine output statement is output, which is used to suggest that the user share the target story with the user's guardian; Obtain the user's response to the statement output by the machine; If the reply indicates agreement to share the target story, then obtain the guardian's contact information from the interactive story account; A communication connection is established with the guardian's terminal device based on the contact information, and a summary of the target story is sent to the guardian's terminal device.

8. A device for cultivating expressive ability based on interactive information, characterized in that, include: A creation unit is used to establish a call connection with a terminal device, which is a device for users to log in to their registered interactive story accounts. The terminal device is located within a training system, which includes a server. The server and the terminal device are connected via a network. The interactive stories associated with the interactive story account include target stories. The calling unit is used to call the target human-computer dialogue engine to interact with the user through the call connection. The human-computer dialogue logic of the target human-computer dialogue engine is given by the interaction script of the target story. The interaction script includes multiple interaction nodes. Each interaction node includes a machine response strategy and user response content. The machine response strategy includes outputting machine statements, and the user response content corresponds to the expected player input statement. The first acquisition unit is used to acquire the user's first input statement in the process data of the interaction; The second acquisition unit is configured to, if the first input statement is a simple type input statement but the current interaction node is a first type interaction node, acquire the first proportion of the number of second type interaction nodes to the total number of the plurality of interaction nodes, and acquire the first number of complex type input statements entered by the user before the current interaction node, wherein the first type interaction node represents the interaction node whose user response content is a complex type input statement, and the second type interaction node represents the interaction node whose user response content is a simple type input statement; The first determining unit is configured to determine the next story node to jump to based on the user response content of the current interaction node and the first input statement if the first ratio is greater than a preset ratio and the first quantity is greater than a preset quantity. The output unit is configured to output a first machine guidance statement in the current interactive node if the first ratio is less than a preset ratio. The first machine guidance statement includes a guidance statement that guides the user to input a preset semantic. The acquisition unit is used to acquire the second input statement from the user in response to the guidance statement of the first machine; The second determining unit is used to determine a score of the user's expressive ability based on the second input statement; The third determining unit is used to determine the next story node to jump to based on the user's response content at the current interaction node and the second input statement if the user's expression ability score exceeds a preset score.

9. An electronic device, characterized in that, include: A processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein, when the processor executes the computer instructions, the electronic device performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1 to 7.

Images