Intelligent agent dialogue processing method and device

Abstract

The embodiment of the invention provides an agent dialogue processing method and device.The agent dialogue processing method comprises the steps that in the agent dialogue process, if a preset instruction submitted by a user through a dialogue interaction page with an agent is obtained, firstly, dialogue records of the user and the agent are obtained according to the preset instruction; performing question extraction in the dialogue record to obtain a question field, generating a question list according to the question field, displaying the question list based on a dialogue interaction page, and if it is detected that a target question in the question list is triggered, skipping to a question display area of the target question; in this way, jumping to the question display area of the target question is achieved in the form of the question list.

Description

TECHNICAL FIELD

[0001] The present document relates to the technical field of artificial intelligence, and in particular to an agent dialogue processing method and device. BACKGROUND

[0002] With the continuous development of the Internet, the dialogue between the agent and the user brings great convenience for data query and data processing of the user. For example, the user can quickly obtain the required data through the dialogue with the agent, and can quickly and accurately perform text processing through the dialogue with the agent without complex and tedious operations. On the basis of improving processing efficiency and processing accuracy, the perception degree of the user to the agent dialogue is improved. How to provide more efficient and more convenient agent dialogue for the user is the focus of the user and the agent provider. SUMMARY

[0003] One or more embodiments of the present specification provide an agent dialogue processing method, comprising: obtaining a dialogue record of a user and an agent according to a preset instruction submitted by the user through a dialogue interaction page of the agent. Extracting a question in the dialogue record to obtain a question field. Generating a question list according to the question field and displaying based on the dialogue interaction page. If it is detected that a target question in the question list is triggered, jumping to a question display area of the target question.

[0004] One or more embodiments of the present specification provide an agent dialogue processing device, comprising: a dialogue record obtaining module configured to obtain a dialogue record of a user and an agent according to a preset instruction submitted by the user through a dialogue interaction page of the agent. A question extraction module configured to extract a question in the dialogue record to obtain a question field. A list generation module configured to generate a question list according to the question field and display based on the dialogue interaction page. If it is detected that a target question in the question list is triggered, a display area jumping module is run, and the display area jumping module is configured to jump to a question display area of the target question.

[0005] One or more embodiments of the present specification provide an agent dialogue processing device, comprising: a processor; and a memory configured to store computer executable instructions which, when executed, cause the processor to: obtain a dialogue record of a user and an agent according to a preset instruction submitted by the user through a dialogue interaction page of the agent. Extract a question in the dialogue record to obtain a question field. Generating a question list according to the question field and displaying based on the dialogue interaction page. If it is detected that a target question in the question list is triggered, jumping to a question display area of the target question.

[0006] The one or more embodiments of the specification provide a computer readable storage medium for storing computer executable instructions, which, when executed, implement the following process: obtaining a dialogue record of a user with an intelligent agent according to a preset instruction submitted by the user through a dialogue interaction page with the intelligent agent. Extracting a question in the dialogue record to obtain a question field. Generating a question list according to the question field and displaying based on the dialogue interaction page. If a target question in the question list is detected to be triggered, jumping to a question display area of the target question. BRIEF DESCRIPTION OF DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the one or more embodiments of the specification or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments described in the specification, and those skilled in the art can also obtain other drawings according to these drawings without creative labor; Figure 1 A schematic diagram of an intelligent agent dialogue processing method implementation environment provided by the one or more embodiments of the specification; Figure 2 A flowchart of an intelligent agent dialogue processing method provided by the one or more embodiments of the specification; Figure 3 A dialogue interaction page schematic diagram provided by the one or more embodiments of the specification; Figure 4 A question list schematic diagram provided by the one or more embodiments of the specification; Figure 5 A question display area schematic diagram provided by the one or more embodiments of the specification; Figure 6 A flowchart of an intelligent agent dialogue processing method applied to an intelligent agent dialogue scenario provided by the one or more embodiments of the specification; Figure 7 A schematic diagram of an intelligent agent dialogue processing device embodiment provided by the one or more embodiments of the specification; Figure 8 A structural schematic diagram of an intelligent agent dialogue processing device provided by the one or more embodiments of the specification. DETAILED DESCRIPTION

[0008] In order to make the person skilled in the art better understand the technical solutions in one or more embodiments of the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of the present specification. Obviously, the described embodiments are only a part of the embodiments of the present specification, not all. Based on one or more embodiments of the present specification, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present document.

[0009] The intelligent agent dialogue processing method provided by one or more embodiments of the present specification can be applied to the implementation environment of the intelligent agent dialogue processing system, which is described with reference to Figure 1 The implementation environment at least includes: A user terminal 101 and a server 102; Wherein, the user interacts with the intelligent agent based on the server 102 through the user terminal 101; The user terminal 101 can be a mobile phone, a personal computer, a tablet computer, an electronic book reader, a device for information interaction based on VR (Virtual Reality, virtual reality technology), a vehicle terminal, an IoT device, a wearable smart device, a laptop computer and a desktop computer, etc.; The user terminal 101 is used to display the dialogue interaction page in the process of user dialogue with the intelligent agent; Wherein, the user can interact with the intelligent agent through the subprogram or webpage in the user terminal 101 for accessing the intelligent agent; The server 102 can be a server, or a server cluster composed of several servers, or one or more cloud servers in a cloud computing platform; For running the intelligent agent; In the implementation environment, the user terminal 101 obtains the dialogue record of the user and the intelligent agent according to the preset instruction submitted by the user through the dialogue interaction page with the intelligent agent, extracts the question field in the dialogue record, generates the question list according to the question field and displays it based on the dialogue interaction page, and if it is detected that the target question in the question list is triggered, jump to the question display area of the target question. In this way, by providing the question list in the dialogue process to the user, the jump to the question display area of the target question is realized.

[0010] One or more embodiments of the intelligent agent dialogue processing method provided by the present specification are as follows: With reference to Figure 2 The intelligent agent dialogue processing method provided by the present embodiment specifically includes steps S202 to S208.

[0011] Step S202, obtaining the dialogue record of the user and the intelligent agent according to the preset instruction submitted by the user through the dialogue interaction page with the intelligent agent.

[0012] In actual application, the user can obtain answers from the intelligent agent through dialogue with the intelligent agent, thereby improving the convenience and efficiency of the user in perceiving the answers; in the specific execution process, the user can dialogue with the intelligent agent through the dialogue interaction page; for example, the user inputs a question through the dialogue interaction page, and the user terminal uploads the question to the server if it detects that the user inputs and submits the question, so as to obtain answers from the intelligent agent and issue the answers to the user terminal, and the user terminal renders the answers to the dialogue interaction page; in the dialogue process between the user and the intelligent agent, multiple rounds of sub-dialogues can be performed, that is, the user inputs and submits multiple questions, in which case, due to the screen limitation of the user terminal, the content displayed is limited, and usually the question input by the user last time and the corresponding answer are displayed; in this case, if the user needs to access the previous question and the corresponding answer, the user needs to slide the dialogue interaction page to find.

[0013] In order to improve the efficiency of the user in anchoring the target question or positioning the target question, the embodiment displays the question list in the dialogue process based on the dialogue interaction page after detecting that the user submits the preset instruction through the dialogue interaction page of the intelligent agent, and anchors the question display area of the target question in the question list if it is detected that the user selects the target question, thereby improving the perception degree of the user on the questions submitted in the dialogue process, improving the convenience and efficiency of the user in accessing the previous questions, and further improving the perception degree of the user on the dialogue with the intelligent agent.

[0014] In the embodiment, the user can dialogue with the intelligent agent through a subprogram and / or a webpage, that is, the user can dialogue with the intelligent agent through a subprogram and / or a webpage; the subprogram can be a subprogram in an application program running on the user terminal, such as an intelligent dialogue subprogram in a payment application program or a resource service subprogram providing intelligent dialogue services or functions; the webpage can be a webpage accessed based on a browser, such as an intelligent dialogue webpage accessed based on a browser or a resource service webpage providing intelligent dialogue services or functions; optionally, the user dialogues with the intelligent agent through a resource service subprogram and / or a resource service webpage. In addition, the user can also dialogue with the intelligent agent through an application program providing intelligent dialogue services or functions, such as an intelligent dialogue application program providing intelligent dialogue services or functions or a payment application program.

[0015] In specific implementation, the preset instruction submitted by the user through the dialogue interaction page of the intelligent agent is acquired. The preset instruction includes a question access instruction for accessing the question in the dialogue process.

[0016] In the specific execution process, the trigger instruction for the preset control in the dialogue interaction page can be taken as the preset instruction, and the preset control includes a control for prompting the anchoring of the question; for example Figure 3The problem anchor control 301 is shown. In an optional embodiment provided by the present embodiment, the preset instruction can be obtained in the following manner: according to a problem triggering operation based on a submitted question in the dialogue interaction page, a preset control is displayed in the dialogue interaction page, and a triggering instruction for the preset control is obtained as the preset instruction. Optionally, the problem triggering operation includes a problem long press operation and / or a problem double-click operation.

[0017] Specifically, the preset instruction submitted by the user through the preset control in the dialogue interaction page with the intelligent agent can be obtained The preset control can be configured in the dialogue interaction page, and correspondingly, the preset instruction can be submitted through the preset control in the dialogue interaction page with the intelligent agent. In addition, the preset control can also be displayed in the dialogue interaction page after a problem triggering operation based on the dialogue interaction page is submitted, and correspondingly, the preset instruction can be submitted through the preset control displayed in the dialogue interaction page after the problem triggering operation based on the dialogue interaction page is submitted.

[0018] As shown in Figure 3 The dialogue interaction page displayed by the user terminal displays question 5 and the answer corresponding to question 5. If a problem long press operation on question 5 is detected, the problem anchor control 301 is displayed, and if an instruction for the problem anchor control 301 is detected, it is determined that the preset instruction is obtained.

[0019] In addition to obtaining the preset instruction for the preset control displayed in the dialogue interaction page, the preset operation based on the dialogue interaction page can also be obtained as the preset instruction. In another optional embodiment provided by the present embodiment, the preset instruction can be obtained in the following manner: the preset operation submitted by the user based on the dialogue interaction page is taken as the preset instruction. Optionally, the preset operation includes a continuous sliding operation on the dialogue interaction page. For example, the continuous upward sliding operation submitted by the user based on the dialogue interaction page is taken as the preset instruction.

[0020] Alternatively, according to the preset operation submitted by the user based on the dialogue interaction page, a preset control can be displayed in the dialogue interaction page, and a triggering instruction for the preset control is obtained as the preset instruction. Correspondingly, the preset operation includes a continuous sliding operation on the dialogue interaction page, and can also include a problem triggering operation on the displayed question.

[0021] In implementation, after the preset instruction submitted by the user through the dialogue interaction page of the agent dialogue is acquired, the dialogue record of the user and the agent can be acquired according to the preset instruction submitted by the user through the dialogue interaction page of the agent dialogue. The dialogue record in the embodiment includes the questions and corresponding answers stored in the dialogue process between the user and the agent. In the embodiment, the user and the agent can ask questions and reply multiple times in a dialogue process. That is, the agent dialogue can include multiple sub-dialogues, and each sub-dialogue in the multiple sub-dialogues is composed of a question submitted by the user and an answer replied by the agent. For example, the user asks 5 times and the agent replies 5 times in an agent dialogue, and the agent dialogue includes 5 sub-dialogues. The acquired dialogue record includes the sub-dialogue records of the 5 sub-dialogues.

[0022] In addition to the dialogue record composed of each sub-dialogue in an agent dialogue process, the dialogue record can also include the dialogue record in the agent dialogue process and the associated dialogue record in the associated agent dialogue process. The associated agent dialogue includes the agent dialogue before the agent dialogue or the agent dialogue where the question associated with the question in the agent dialogue is located. The embodiment does not limit here.

[0023] It should be noted that the one or more agent dialogue processing methods provided in the embodiment can be applied to a user terminal. In the process of acquiring the dialogue record of the user and the agent according to the preset instruction, the user terminal can acquire the locally stored dialogue record of the user and the agent. In addition, if the locally stored dialogue record is empty, the dialogue record of the user and the agent can also be acquired from the server. Specifically, the user terminal sends a question access request to the server according to the preset instruction, the server reads the stored dialogue record in response to the question access request and returns to the user terminal. Alternatively, the user terminal can also acquire the dialogue record locally and acquire the associated dialogue record from the server. For example, the user terminal acquires the locally stored dialogue record according to the preset instruction, sends a question access request carrying the dialogue record to the server, and the server reads the associated dialogue record according to the dialogue record carried by the question access request and returns to the user terminal.

[0024] In addition, step S202 can be replaced by acquiring the dialogue record of the agent dialogue according to the preset instruction submitted by the user through the dialogue interaction page of the agent dialogue, and combining with other processing steps provided in the embodiment to form a new implementation mode.

[0025] In step S204, the question extraction is performed in the dialogue record to obtain a question field.

[0026] In implementation, after the dialogue record of the user and the agent is acquired according to the preset instruction submitted by the user through the dialogue interaction page of the agent dialogue, the question extraction is performed in the dialogue record to obtain a question field.

[0027] In the process of extracting the question from the dialogue record and obtaining the question field, the question in the dialogue record can be extracted as the question field. In addition, in order to improve the effectiveness of the obtained question field and the perception of the user to the question field, and to avoid the problem that the content of the question is too long or the number of characters is too large, which affects the display of the question in the subsequent question list, the question in the dialogue record can be extracted as a key field to obtain a key question field as the question field. In an optional implementation provided by the embodiment, in the process of extracting the question from the dialogue record and obtaining the question field, the following operations are performed: extracting a plurality of questions in the dialogue record, and determining a field extraction manner of each question according to a question parameter of each question; extracting a key field of each question according to the field extraction manner to obtain the question field.

[0028] Specifically, the field extraction manner of each question is determined according to the question parameter of each question in the dialogue record, and the key field of each question is extracted according to the field extraction manner to obtain the question field.

[0029] Optionally, the question parameter includes the question length, the number of characters of the question, and / or the question category. The field extraction manner can include a preset content extraction manner and / or a semantic extraction manner.

[0030] For example, if the question length of the question is less than a preset length or the number of characters of the question is less than a preset number of characters, the field extraction manner is determined as a first field extraction manner; wherein the first field extraction manner includes taking the question as the question field; that is, if the question length of the question is less than the preset length or the number of characters of the question is less than the preset number of characters, the question is taken as the question field.

[0031] For another example, if the question length is greater than or equal to the preset length, or the number of characters of the question is greater than or equal to the preset number of characters, the field extraction manner is determined as a second field extraction manner; wherein the second field extraction manner includes a semantic extraction manner; that is, if the question length is greater than or equal to the preset length, or the number of characters of the question is greater than or equal to the preset number of characters, the question is semantically recognized, and the semantic recognition result is taken as the question field.

[0032] For another example, if the question type is a file analysis type, and the question length is less than a preset length or the number of characters of the question is less than a preset number of characters, the field extraction manner is determined as a third field extraction manner; wherein the third field extraction manner includes a preset content extraction manner; that is, if the question type is a file analysis type, and the question length is less than the preset length or the number of characters of the question is less than the preset number of characters, the file name is extracted, and the file name and the question are spliced to obtain the question field.

[0033] For another example, if the question type is a file analysis type and the question length is greater than or equal to a preset length or the question character number is greater than or equal to a preset character number, it is determined that the field extraction manner is a fourth field extraction manner; the fourth field extraction manner includes extracting a file name and performing semantic recognition on the question, and splicing the file name and the semantic recognition result to obtain the question field.

[0034] For another example, if the question type is a data processing type and the question length is less than a preset length or the question character number is less than a preset character number, it is determined that the field extraction manner is the first field extraction manner.

[0035] The above process of determining the corresponding field extraction manner according to different question parameters, extracting the key field of each question according to the field extraction manner, and obtaining the question field is described in detail, and it should be noted that the above five implementation manners can be combined and extracted according to actual needs, which is not limited in this embodiment.

[0036] In addition, steps S202 to S204 can be replaced by extracting questions in the dialogue record according to a preset instruction submitted by the user through the dialogue interaction page with the agent, obtaining the question field, and combining with other processing steps provided in this embodiment to form a new implementation manner.

[0037] Step S206: generating a question list according to the question field and displaying the question list based on the dialogue interaction page.

[0038] On the basis of obtaining the question field, generating a question list according to the question field and displaying the question list based on the dialogue interaction page.

[0039] In a specific implementation, in order to improve the effectiveness of the generated question list, the plurality of question fields are arranged in descending order according to the question submission time corresponding to each question field to obtain the question list; on this basis, in order to improve the user's perception of the question submission time of each question field in the question list, the question submission time corresponding to each question field can also be updated to the question list; based on this, in an optional implementation manner provided in this embodiment, in the process of generating the question list according to the question field, the following operations are performed: arranging the plurality of question fields in descending order according to the question submission time corresponding to each question field to obtain an initial question list; updating the question submission time to the initial question list to obtain the question list.

[0040] Specifically, the plurality of question fields are arranged in descending order according to the question submission time corresponding to each question field to obtain a question list containing the question submission time of each question. Optionally, the question submission time corresponding to each question field can be read in the dialogue record.

[0041] After generating the question list according to the question fields, in order to make the user perceive the question list, the question list is displayed based on the dialogue interaction page; optionally, the question list can be displayed on the upper layer of the dialogue interaction page through a pop-up window component.

[0042] For example Figure 4 As shown, the question list is displayed on the upper layer of the dialogue interaction page through the pop-up window component; the question list displays a plurality of question fields and question submission times corresponding to each question field; the user can select a target question through the question list to jump to the question display area of the target question; and the pop-up window component can also display a cancel control 401 during the process of displaying the question list, and the user can return to the dialogue interaction page through the cancel control. It should be noted that returning to the dialogue interaction page includes returning to the current display area of the dialogue interaction page.

[0043] It should be noted that if the dialogue record of the agent dialogue and the associated dialogue record associated with the agent dialogue are obtained, the question extraction can be performed in the dialogue record to obtain the question field, and the question extraction can be performed in the associated dialogue record to obtain the associated question field; the question list is generated according to the question field, and the associated question list is generated according to the associated question field; the question list is displayed based on the dialogue interaction page, and if it is detected that a list switching instruction is submitted through the question list displayed based on the dialogue interaction page, the associated question list is displayed based on the dialogue interaction page. The question extraction of the associated dialogue record and the generation process of the associated question list are similar to the question extraction of the dialogue record and the generation process of the question list described above, and reference can be made to the related contents described above; if a target associated question in the associated question list is triggered, the related contents of the target question in the question list being triggered can be performed, which is not limited in this embodiment.

[0044] In step S208, if it is detected that a target question in the question list is triggered, jump to the question display area of the target question.

[0045] In specific implementation, after generating the question list according to the question fields and displaying the question list based on the dialogue interaction page, if it is detected that a target question in the question list is triggered, jump to the question display area of the target question, so as to improve the convenience of the user for querying the target question.

[0046] In the specific implementation process, if the user terminal detects that a target question in the question list is triggered, the user terminal can jump to the question display area of the target question in the locally stored dialogue interaction page; in an optional implementation manner provided by this embodiment, the jump to the question display area of the target question is realized in the following manner: determine first position information of the dialogue interaction page for question display and second position of the target question in the locally stored dialogue interaction page; The sliding parameter is calculated according to the first position and the second position, and the dialogue interaction page is handled according to the sliding parameter to display the question display area.

[0047] Optionally, the first position information includes position information of a displayed question in the dialogue interaction page in the current display area. The dialogue interaction page can be long, and the terminal screen can display a partial display area of the dialogue interaction page.

[0048] Specifically, if the target question in the question list is detected to be triggered, in the process of jumping from the current display area in the dialogue interaction page to the question display area of the target question, first, the first position information of the displayed question in the current display area in the dialogue interaction page and the second position information of the target question in the locally stored dialogue interaction page are determined, then the sliding parameter is calculated according to the first position information and the second position information, and the dialogue interaction page is handled according to the sliding parameter to display the question display area.

[0049] For example Figure 5 As shown, the first position information of the displayed question in the current display area of the dialogue interaction page in the dialogue interaction page is determined to be p1, and the second position information of the selected question 3 in the locally stored dialogue interaction page is determined to be p2; wherein p2 < p1; the sliding distance is calculated according to p1-p2, and since p2 < p1, the sliding direction is determined to be up, then the dialogue interaction page is slid up by a distance of p1-p2, and the question display area of the question 3 is displayed.

[0050] In the process of handling the dialogue interaction page, since the display of the to-be-displayed question and the corresponding answer is to be performed, if it is detected in the sliding process that the answer of the locally stored to-be-displayed question is empty, the to-be-displayed question is uploaded to the server, the server queries the stored answer of the to-be-displayed question or replies to the to-be-displayed question through an intelligent agent; the user terminal performs dialogue interaction page rendering and sliding processing according to the to-be-displayed question and the to-be-displayed answer returned by the server; that is, if it is detected in the sliding process that the answer of the locally stored to-be-displayed question is empty, the to-be-displayed answer of the to-be-displayed question is obtained from the server, and the to-be-displayed area of the dialogue interaction page is rendered according to the to-be-displayed question and the to-be-displayed answer and the sliding processing is continued.

[0051] Further, the user terminal can jump to a target dialogue interaction page rendered according to the target question and the corresponding answer if the target question in the problem list is detected to be triggered; wherein, the target dialogue interaction page can be rendered according to the target question and the locally stored answer, or can be rendered according to the target question and the answer returned by the server; based on the target question and the second optional implementation provided in the embodiment, the target question is uploaded to the server in the process of jumping to the question display area of the target question, the server queries the stored answer or replies to the target question based on the intelligent agent, the user terminal renders the target dialogue interaction page according to the target question and the answer returned by the server, and jumps from the dialogue interaction page being displayed to the target dialogue interaction page.

[0052] It should be noted that, in addition to rendering the target dialogue interaction page according to the target question and the answer, the target dialogue interaction page can also be rendered according to the target question, the answer, the associated question and the associated answer; optionally, the associated question includes at least one of the following: a bit associated question of the target question, a semantic associated question of the target question, and a content associated question of the target question.

[0053] In the process of rendering the target dialogue interaction page according to the target question, the answer, the associated question and the associated answer, the associated question and the associated answer of the target question can be obtained first, and then the target dialogue interaction page can be rendered according to the target question, the answer corresponding to the target question, the associated question and the associated answer; further, in the process of jumping to the question display area, the dialogue interaction page can be jumped to the target dialogue interaction page. In order to improve the effectiveness of the obtained associated question and associated answer, before obtaining the associated question and the associated answer, the screen display parameters of the target question and the answer can be determined according to the target question, the answer and the field rendering parameter; if the screen display parameters match the screen display threshold successfully, the target dialogue interaction page is rendered according to the target question and the answer; if the screen display parameters fail to match the screen display threshold, the associated question and the associated answer of the target question are obtained, and the target dialogue interaction page is rendered according to the target question, the answer, the associated question and the associated answer. Optionally, the screen display parameter includes a screen display length, and the screen display threshold includes a terminal screen length; if the length difference between the screen display length and the terminal screen length is less than a preset threshold, it is determined that the matching is successful; otherwise, it is determined that the matching fails.

[0054] Wherein, the associated question and the associated answer of the target question can be obtained by uploading the target question to the server to determine the associated question and the associated answer and returning to the user terminal.

[0055] To sum up, the embodiment provides one or more agent dialogue processing methods. If a preset instruction submitted by a user through a dialogue interaction page of an agent dialogue is acquired, dialogue records of the agent dialogue are acquired and question extraction is performed in the dialogue records, a question field is obtained, a question list is generated according to the question field and is displayed on an upper layer of the dialogue interaction page, so that the user can conveniently and efficiently select a target question in a hidden answer manner. If it is detected that the target question in the question list is triggered, the current display area is jumped to a question display area of the target question, so that the efficiency and accuracy of the user in searching for the target question are improved, and the perception of the user to the agent dialogue is improved.

[0056] The following further describes the agent dialogue processing method provided in the embodiment by taking application of the agent dialogue processing method provided in the embodiment in an agent dialogue scene as an example, as shown in Figure 6 The agent dialogue processing method applied in the agent dialogue scene specifically includes the following steps.

[0057] In step S602, a question access instruction submitted by a user through a current display area of a dialogue interaction page of an agent dialogue is acquired.

[0058] In step S604, dialogue records are read from a local storage according to the question access instruction, and a plurality of questions in the dialogue records and question submission times of the questions are extracted.

[0059] In step S606, the plurality of questions are arranged in descending order according to the question submission times of the questions, and a question list is obtained.

[0060] In step S608, the question list is displayed on an upper layer of the current display area through a pop-up window component.

[0061] In step S610, if it is detected that a target question in the question list is triggered, first position information of a display question in the dialogue interaction page in the current display area and second position information of the target question in the dialogue interaction page are determined.

[0062] In step S612, sliding processing is performed according to the first position information and the second position information, so that the current display area is slid to a question display area of the target question.

[0063] It should be noted that any one of steps S602 to S612 or a combination of any multiple steps can be combined with any one of steps S202 to S208 or a combination of any multiple steps to form a new implementation manner according to the needs of implementation deployment. In addition, any one or more technical features of steps S602 to S612 can be combined with any one or more technical features provided by steps S202 to S208 to form a new implementation manner according to the actual deployment needs. Alternatively, any one or more technical features of steps S602 to S612 can also be replaced by a combination of any one or more technical features provided by steps S202 to S208 to form a new implementation manner according to the actual deployment needs, which will not be described one by one here.

[0064] The embodiment of the agent dialogue processing device provided in the specification is implemented, for example, as follows: In the above embodiment, an agent dialogue processing method is provided, and a corresponding agent dialogue processing device is also provided, which will be described below with reference to the accompanying drawings.

[0065] Reference Figure 7 It shows a schematic diagram of an embodiment of an agent dialogue processing device provided by the embodiment.

[0066] Since the device embodiment corresponds to the method embodiment, the description is relatively simple, and the related parts can be seen from the above-mentioned corresponding description of the method embodiment. The device embodiment described below is only illustrative.

[0067] The embodiment provides an agent dialogue processing device, which comprises: The dialogue record acquisition module 702 is configured to acquire dialogue records of a user and an agent according to preset instructions submitted by the user through a dialogue interaction page with the agent; The question extraction module 704 is configured to extract questions in the dialogue records to obtain a question field; The list generation module 706 is configured to generate a question list according to the question field and display based on the dialogue interaction page; If it is detected that a target question in the question list is triggered, the display area jump module 708 is run, and the display area jump module 708 is configured to jump to a question display area of the target question.

[0068] The embodiment of the agent dialogue processing device provided in the specification is implemented, for example, as follows: Corresponding to the above-described intelligent agent dialogue processing method, based on the same technical concept, one or more embodiments of the present specification also provide an intelligent agent dialogue processing device for executing the above-described intelligent agent dialogue processing method, Figure 8 A structural schematic diagram of an intelligent agent dialogue processing device provided by one or more embodiments of the present specification.

[0069] The intelligent agent dialogue processing device provided by the present embodiment comprises: As Figure 8 As shown, the intelligent agent dialogue processing device can have a large difference due to different configurations or performances, and can include one or more processors 801 and memories 802, and the memories 802 can store one or more storage applications or data. Among them, the memory 802 can be temporary storage or persistent storage. The application stored in the memory 802 can include one or more modules (not shown in the figure), and each module can include a series of computer executable instructions in the intelligent agent dialogue processing device. Further, the processor 801 can be configured to communicate with the memory 802 and execute a series of computer executable instructions in the memory 802 on the intelligent agent dialogue processing device. The intelligent agent dialogue processing device can also include one or more power supplies 803, one or more wired or wireless network interfaces 804, one or more input / output interfaces 805, one or more keyboards 806, etc.

[0070] In a specific embodiment, the intelligent agent dialogue processing device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs can include one or more modules, and each module can include a series of computer executable instructions in the intelligent agent dialogue processing device, and the one or more processors configured to execute the one or more programs include computer executable instructions for: According to the preset instruction submitted by the user through the dialogue interaction page with the intelligent agent, the dialogue record of the user and the intelligent agent is obtained; Question extraction is performed in the dialogue record to obtain a question field; Generating a question list according to the question field and displaying based on the dialogue interaction page; If it is detected that a target question in the question list is triggered, jump to the question display area of the target question.

[0071] The computer readable storage medium implementation provided by the present specification is as follows: Corresponding to the above-described intelligent agent dialogue processing method, based on the same technical concept, one or more embodiments of the present specification also provide a computer-readable storage medium.

[0072] The computer-readable storage medium provided by the embodiment provides computer-executable instructions for storing, and the computer-executable instructions realize the following processes when executed: According to the preset instruction submitted by the user through the dialogue interaction page with the intelligent agent, the dialogue record of the user and the intelligent agent is obtained; Question extraction is performed in the dialogue record to obtain a question field; A question list is generated according to the question field and is displayed based on the dialogue interaction page; If it is detected that a target question in the question list is triggered, jump to the question display area of the target question.

[0073] It should be noted that the embodiments of the computer-readable storage medium in the present specification and the embodiments of the intelligent agent dialogue processing method in the present specification are based on the same inventive concept, so the specific implementation of the embodiments can be referred to the foregoing implementation of the corresponding method, and the repeated parts will not be described herein.

[0074] The computer program product provided by the present specification is implemented as follows: Corresponding to the above-described intelligent agent dialogue processing method, based on the same technical concept, one or more embodiments of the present specification also provide a computer program product.

[0075] A computer program product includes computer programs / instructions, which, when executed by a processor, realize the following steps: According to the preset instruction submitted by the user through the dialogue interaction page with the intelligent agent, the dialogue record of the user and the intelligent agent is obtained; Question extraction is performed in the dialogue record to obtain a question field; A question list is generated according to the question field and is displayed based on the dialogue interaction page; If it is detected that a target question in the question list is triggered, jump to the question display area of the target question.

[0076] It should be noted that the embodiments of the computer-readable storage medium in the present specification and the embodiments of the intelligent agent dialogue processing method in the present specification are based on the same inventive concept, so the specific implementation of the embodiments can be referred to the foregoing implementation of the corresponding method, and the repeated parts will not be described herein.

[0077] The various embodiments in the specification are described in progressive manner, and the same or similar parts among the various embodiments can be referred to each other, and each embodiment focuses on the difference from other embodiments, such as the device embodiment, the equipment embodiment and the computer readable storage medium embodiment, which are similar to the method embodiment, so the description is relatively simple, and the related content in the device embodiment, the equipment embodiment and the computer readable storage medium embodiment can be read with reference to the part of the method embodiment.

[0078] The above describes specific embodiments of the specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than the order in which they are recited and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or necessary.

[0079] In the 1930s, it was clear to distinguish whether an improvement in a technology was in hardware (e.g., improvement in circuit structure of diodes, transistors, switches, etc.) or in software (e.g., improvement in method flow). However, as technology has evolved, many improvements in method flow today can be considered as direct improvements in hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using hardware entity modules. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. A digital system is "integrated" on a PLD by the designer programming it, rather than by asking a chip manufacturer to design and fabricate a custom integrated circuit chip. Moreover, instead of manually fabricating integrated circuit chips, this programming is now mostly implemented using "logic compiler" software, which is similar to software compilers used in program development, and the original code before compilation is written in a specific programming language, which is called a hardware description language (HDL), and there are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., and the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should be aware that only a little logical programming of the method flow in the above-mentioned hardware description languages and programming into an integrated circuit can easily obtain a hardware circuit that implements the logical method flow.

[0080] The controller can be implemented in any suitable way, for example, the controller can take the form of a microprocessor or processor and a computer readable medium storing computer readable program code, such as software or firmware, executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that, in addition to implementing the controller in pure computer readable program code, it is also possible to implement the controller in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers, etc. to perform the same functions by logically programming the method steps. Such a controller can therefore be considered as a hardware component, and the means included therein for performing various functions can also be considered as structures within the hardware component. Alternatively, the means for performing various functions can even be considered as both a software module implementing the method and a structure within the hardware component.

[0081] The systems, apparatuses, modules or units illustrated by the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0082] For the sake of brevity, the above apparatuses are described in functional form in various units. Of course, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0083] Those skilled in the art will appreciate that one or more embodiments of the disclosure can provide a method, a system or a computer program product. Accordingly, one or more embodiments of the disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the disclosure can take the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0084] The specification is presented with reference to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams can represent one or more of any appropriate circuitry configured to perform the specified functions. In this regard, one or more flow diagrams and / or block diagrams in the flow diagrams and / or block diagrams can represent a device, such as a device configured to perform the specified functions, or one or more devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams and / or a combination of devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams can represent one or more of any appropriate circuitry configured to perform the specified functions. In this regard, one or more flow diagrams and / or block diagrams in the flow diagrams and / or block diagrams can represent a device, such as a device configured to perform the specified functions, or one or more devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams and / or a combination of devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams.

[0085] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow diagrams and / or block diagrams flow or flows and / or block or blocks specified in the flow diagrams and / or block diagrams. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams can represent one or more of any appropriate circuitry configured to perform the specified functions. In this regard, one or more flow diagrams and / or block diagrams in the flow diagrams and / or block diagrams can represent a device, such as a device configured to perform the specified functions, or one or more devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams and / or a combination of devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams can represent one or more of any appropriate circuitry configured to perform the specified functions. In this regard, one or more flow diagrams and / or block diagrams in the flow diagrams and / or block diagrams can represent a device, such as a device configured to perform the specified functions, or one or more devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams and / or a combination of devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams.

[0086] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow diagrams and / or block diagrams flow or flows and / or block or blocks specified in the flow diagrams and / or block diagrams. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams can represent one or more of any appropriate circuitry configured to perform the specified functions. In this regard, one or more flow diagrams and / or block diagrams in the flow diagrams and / or block diagrams can represent a device, such as a device configured to perform the specified functions, or one or more devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams and / or a combination of devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams can represent one or more of any appropriate circuitry configured to perform the specified functions. In this regard, one or more flow diagrams and / or block diagrams in the flow diagrams and / or block diagrams can represent a device, such as a device configured to perform the specified functions, or one or more devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams and / or a combination of devices configured to perform the specified functions in the one or more flow diagrams and / or block diagrams.

[0087] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0088] The memory can include non-persistent memory, random access memory (RAM), and / or non-volatile memory, etc. in the form of computer-readable media, such as read only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0089] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0090] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, such that processes, methods, articles or devices that comprise a list of elements not only include those elements, but also include other elements not expressly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the phrase "comprising at least one" does not exclude the presence of additional identical elements in the process, method, article or device that includes the element.

[0091] One or more embodiments of the present specification can be described in the general context of computer-executable instructions being executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0092] The above only describes the embodiments of the present document and is not intended to limit the present document. For those skilled in the art, the present document can have various changes and variations. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present document shall be included in the scope of claims of the present document.

Claims

1. An intelligent agent conversation processing method, comprising: obtaining a conversation record of a user with an intelligent agent according to a preset instruction submitted by the user through a conversation interaction page with the intelligent agent; extracting a question field in the conversation record; generating a question list according to the question field and displaying the question list based on the conversation interaction page; if a target question in the question list is detected to be triggered, jumping to a question display area of the target question.

2. The intelligent agent conversation processing method of claim 1, wherein the preset instruction is obtained in the following manner: displaying a preset control through the conversation interaction page according to a question submission trigger operation based on a displayed question in the conversation interaction page; obtaining a trigger instruction for the preset control as the preset instruction.

3. The intelligent agent conversation processing method of claim 1, wherein the jumping to the question display area of the target question comprises: determining first position information of the conversation interaction page for question display and second position information of the target question in the locally stored conversation interaction page; calculating a sliding parameter according to the first position information and the second position information, and performing sliding processing on the conversation interaction page according to the sliding parameter to display the question display area.

4. The intelligent agent conversation processing method of claim 1, wherein the generating a question list according to the question field comprises: performing descending order arrangement on a plurality of question fields according to question submission times corresponding to the question fields to obtain an initial question list; updating the question submission times to the initial question list to obtain the question list.

5. The intelligent agent conversation processing method of claim 1, wherein the jumping to the question display area of the target question comprises: uploading the target question to a server; the server querying a stored answer or replying to the target question based on the intelligent agent; rendering a target conversation interaction page according to the target question and the answer returned by the server, and jumping from the conversation interaction page to the target conversation interaction page.

6. The agent conversation handling method of claim 1, the presenting based on the conversation interaction page comprising: displaying the target conversation interaction page on an upper layer of the conversation interaction page through a pop-up window component.

7. The intelligent agent conversation processing method of claim 1, wherein the user performs intelligent agent conversation through a resource service subprogram and / or a resource service web page; the intelligent agent conversation comprises a plurality of sub-conversations, and each sub-conversation in the plurality of sub-conversations is composed of a question submitted by the user and an answer replied by the intelligent agent.

8. The intelligent agent conversation processing method of claim 1, wherein the jumping to the question display area of the target question comprises: obtaining an associated question and an associated answer of the target question; rendering a target conversation interaction page according to the target question, an answer corresponding to the target question, the associated question and the associated answer, and jumping from the conversation interaction page to the target conversation interaction page.

9. The intelligent agent conversation processing method of claim 8, further comprising, before the obtaining an associated question and an associated answer of the target question sub-step is executed: determine screen display parameters of the target question and the answer according to the target question, the answer and field rendering parameters; if the screen display parameters fail to match screen display threshold values, perform the sub-step of obtaining associated questions and associated answers of the target question.

10. The intelligent agent dialogue processing method of claim 8, wherein the associated questions comprise at least one of the following: position-associated questions of the target question, semantic-associated questions of the target question, and content-associated questions of the target question.

11. The intelligent agent dialogue processing method of claim 3, wherein the sliding processing of the dialogue interaction page according to the sliding parameters comprises: if it is detected that answers of to-be-displayed questions stored locally are empty during the sliding process, uploading the to-be-displayed questions to the server; performing dialogue interaction page rendering according to the to-be-displayed questions and to-be-displayed answers returned by the server and performing the sliding processing.

12. The intelligent agent dialogue processing method of claim 1, wherein the preset instruction is obtained in the following manner: taking a preset operation submitted by the user based on the dialogue interaction page as the preset instruction; wherein the preset operation comprises a continuous sliding operation on the dialogue interaction page.

13. The intelligent agent dialogue processing method of claim 1, wherein the question extraction in the dialogue record to obtain question fields comprises: extracting multiple questions in the dialogue record, determining field extraction manners of the questions according to question parameters of the questions; and performing key field extraction on the questions according to the field extraction manners to obtain question fields.

14. An intelligent agent dialogue processing apparatus, comprising: a dialogue record obtaining module configured to obtain dialogue records of a user with an intelligent agent according to a preset instruction submitted by the user through a dialogue interaction page with the intelligent agent; a question extracting module configured to extract questions in the dialogue records to obtain question fields; a list generating module configured to generate a question list according to the question fields and display the question list based on the dialogue interaction page; if it is detected that a target question in the question list is triggered, running a display area jumping module configured to jump to a question display area of the target question.

15. An intelligent agent dialogue processing device, comprising: a processor; and a memory configured to store computer executable instructions which, when executed, cause the processor to: obtain dialogue records of a user with an intelligent agent according to a preset instruction submitted by the user through a dialogue interaction page with the intelligent agent; extract questions in the dialogue records to obtain question fields; generate a question list according to the question fields and display the question list based on the dialogue interaction page; if it is detected that a target question in the question list is triggered, jump to a question display area of the target question.

16. A computer readable storage medium for storing computer executable instructions which, when executed, implement the steps of the method of claim 1.

Images