A data processing method, device and equipment and computer storage medium

Abstract

This application provides a method, apparatus, and device for data processing, as well as a computer storage medium. The method relates to the field of intelligent response technology and is applied to an intelligent response system, which includes machine response and human response. The method includes: acquiring input data received by the intelligent response system; the input data includes input data from the questioner and input data from the human responder; performing keyword detection on the input data based on a preset keyword set to obtain corresponding target detection results; the target detection results include the overall distribution information of target key data in the keyword set within the input data; if, based on the target detection results, it is determined that target key data exists in the input data, then obtaining the order of appearance of the target key data based on the overall distribution information; based on the order of appearance and combined with a preset response data set, outputting corresponding target response data to the source of the input data respectively.

Description

Technical Field

[0001] This application relates to the field of intelligent response technology, specifically to a data processing method, apparatus, device, and computer storage medium. Background Technology

[0002] With the continuous development of internet technology, intelligent responses are widely used in various industries. Service providers use intelligent responses to pre-set questions and corresponding answers, so that when users have relevant questions, they can quickly get answers through this intelligent response method.

[0003] However, in typical intelligent response processes, since they can only mechanically reply to user questions based on preset questions and answers, they cannot provide timely feedback based on changes in the user's status. This reduces the user experience and results in poor response quality and low problem-solving efficiency.

[0004] Therefore, how to improve the response effect and the corresponding user experience during the intelligent response process is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a data processing method, apparatus, device, and computer storage medium to improve the response effect and corresponding user experience during the intelligent response process.

[0006] In a first aspect, embodiments of this application provide a data processing method applied to an intelligent response system, the intelligent response system including machine response and human response, the method comprising: acquiring input data received by the intelligent response system; wherein the input data includes: input data from the questioner and input data from the human responder; performing keyword detection on the input data based on a preset keyword set to obtain corresponding target detection results; wherein the target detection results include: overall distribution information of target key data in the keyword set in the input data; if, based on the target detection results, it is determined that the target key data exists in the input data, then obtaining the appearance order of the target key data based on the overall distribution information; and, based on the appearance order and combined with a preset response data set, outputting corresponding target response data to the source of the input data respectively.

[0007] In this solution, keyword detection is performed on the input data from both the questioner and the human responder in the intelligent response system. This yields target detection results indicating the overall distribution of key target data. Based on the distribution of key target data within the input data of both parties, targeted response data is output to each party, improving the user experience and mitigating potential emotional conflicts, thus effectively increasing the efficiency of resolving the questioner's doubts. Furthermore, by using key target data from the keyword set for keyword identification, semantic analysis of the input data is eliminated. Instead, it only requires determining whether characters in the input data match the target key data. This speeds up the server's response to the target key data and avoids the computational resource consumption associated with semantic analysis.

[0008] Optionally, the step of outputting corresponding target response data to the source of the input data based on the order of occurrence and in combination with a preset set of response data includes: obtaining the cumulative number of times the target key data appears in one party's input data within a preset time range based on the overall distribution information; obtaining the target response data corresponding to the order of occurrence and the cumulative number of occurrences from the set of response data based on the order of occurrence and the cumulative number of occurrences, and outputting the target response data to the source party.

[0009] In this approach, based on the order of appearance and cumulative frequency of the target key data, different target response data are selected and output to the questioner and the human responder respectively. This makes the response data more targeted to different situations, further improving the efficiency of alleviating the current emotional conflict and enhancing the user experience for both parties.

[0010] Optionally, after outputting the corresponding target response data to the sources of the input data respectively, the method further includes: selecting input data from the input data from the questioner that does not contain the target key data as target input data, and saving the target input data to a preset storage address; and saving all the input data from the human responder to the preset storage address.

[0011] In this approach, filtering and storing the data from the problem-raiser can avoid storing key target data, reduce the probability of storing dirty data in the database, and reduce the pressure on maintenance personnel to collect statistics. Storing all the data from the human responders can facilitate the assessment of human responders and provide them with a data foundation.

[0012] Optionally, when the input data only contains input data from the questioner, the method further includes: obtaining a target number of times the target key data appears in the input data within a preset time range; associating the questioner with a corresponding emotion tag based on the target number of times; and sending the emotion tag associated with the questioner to the human responder before the human responder accesses the intelligent response system.

[0013] In this approach, a corresponding emotion tag is assigned to the questioner, and this emotion tag is sent to the human responder who will be connected to the intelligent response system. This allows the human responder to obtain the emotion assessment results of the questioner in advance, making it easier for them to adjust their response accordingly. In this way, the user experience of both parties can be improved simultaneously.

[0014] Optionally, before acquiring the input data received by the intelligent response system, the method further includes: acquiring at least one keyword; converting the at least one keyword according to a preset format to obtain corresponding target key data, and storing the target key data in the keyword set.

[0015] In this approach, keywords are stored in a keyword set in a unified format through format conversion, which effectively improves the compatibility of the keyword set and enhances the practicality of the solution.

[0016] Secondly, this application provides a data processing apparatus applied to an intelligent response system, the intelligent response system including machine response and human response, the apparatus comprising: an acquisition module, used to acquire input data received by the intelligent response system; wherein the input data includes: input data from the questioner and input data from the human responder; a processing module, used to perform keyword detection on the input data based on a preset keyword set, and obtain corresponding target detection results; wherein the target detection results include: the overall distribution information of target key data in the keyword set in the input data; if, based on the target detection results, it is determined that the target key data exists in the input data, then the appearance order of the target key data is obtained based on the overall distribution information; and an output module, used to output corresponding target response data to the source of the input data based on the appearance order and in conjunction with a preset response data set.

[0017] Optionally, when the output module outputs corresponding target response data to the source of the input data based on the order of occurrence and in combination with a preset response data set, it is specifically configured to: based on the overall distribution information, obtain the cumulative number of times the target key data appears in one party's input data within a preset time range; based on the order of occurrence and the cumulative number of times, obtain the target response data corresponding to the order of occurrence and the cumulative number of times from the response data set, and output the target response data to the source party.

[0018] Optionally, the device further includes a storage module. After the output module outputs the corresponding target response data to the source of the input data, the storage module is configured to: select input data from the input data from the questioner that does not contain the target key data as target input data and save the target input data to a preset storage address; and save all the input data from the human responder to the preset storage address.

[0019] Optionally, when the input data only contains input data from the questioner, the processing module is further configured to: obtain the target number of times the target key data appears in the input data within a preset time range; associate the questioner with the corresponding emotion tag based on the target number; and send the emotion tag associated with the questioner to the human responder before the human responder accesses the intelligent response system.

[0020] Optionally, before acquiring the input data received by the intelligent response system, the acquisition module is further configured to: acquire at least one keyword; convert the at least one keyword according to a preset format to obtain corresponding target key data, and store the target key data in the keyword set.

[0021] Thirdly, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor, by executing the instructions stored in the memory, causes the at least one processor to perform the method described in the first aspect or any optional embodiment of the first aspect.

[0022] Fourthly, a computer-readable storage medium is provided for storing instructions that, when executed, cause a method as described in the first aspect or any alternative embodiment of the first aspect to be implemented.

[0023] Fifthly, a computer program product containing instructions is provided, the computer program product storing instructions that, when run on a computer, cause the computer to perform the method as described in the first aspect or any optional embodiment of the first aspect.

[0024] The technical effects or advantages of one or more technical solutions provided in the second, third, fourth and fifth aspects of this application can all be explained by the corresponding technical effects or advantages of one or more technical solutions provided in the first aspect. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram illustrating possible application scenarios provided for embodiments of this application;

[0027] Figure 2 A flowchart illustrating a data processing method provided in an embodiment of this application;

[0028] Figure 3 A flowchart illustrating a method for obtaining a keyword set as provided in an embodiment of this application;

[0029] Figure 4 A flowchart illustrating a method for outputting target response data provided in an embodiment of this application;

[0030] Figure 5 A flowchart illustrating a method for assigning emotion tags according to an embodiment of this application;

[0031] Figure 6 A logical schematic diagram of a data processing method provided in an embodiment of this application;

[0032] Figure 7 This is a schematic diagram of the structure of a statistical information collection device provided in an embodiment of this application;

[0033] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0034] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0035] It should be understood that in the description of the embodiments of this application, terms such as "first" and "second" are used only for the purpose of distinguishing descriptions and should not be construed as indicating or implying relative importance, nor should they be construed as indicating or implying order. In the description of the embodiments of this application, "multiple" refers to two or more.

[0036] The term "and / or" in the embodiments of this application is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0037] In this embodiment of the application, the collection, dissemination, and use of data all comply with the requirements of relevant national laws and regulations.

[0038] Intelligent response systems, through pre-set questions and answers, can provide satisfactory solutions for most users, and therefore have been widely used in various industries. With computer-controlled intelligent response systems, human customer service representatives are freed from a large number of repetitive questions and answers, allowing them to focus their energy more accurately on users' complex issues.

[0039] However, before human customer service is available, some users may experience significant emotional fluctuations due to the frustration of their problems not being resolved in a timely manner. When faced with this situation, the intelligent response system can only repeat its answers, which will cause the user's emotions to accumulate. When human customer service representatives face users in this state, they may also experience corresponding emotional fluctuations, thus reducing the experience for both parties.

[0040] In view of this, this application provides a data processing method, apparatus, device, and computer storage medium. By performing line-specific keyword detection on the data of both parties, when preset target key data exists in the input data of both parties, based on the overall distribution information of the target key data in all input data, different target response data is output for different data sources. Thus, when key words appear in the input data, different response processing can be performed for each party, reducing the degree of emotional fluctuation for both parties and effectively improving the user experience for both, thereby avoiding the occurrence of extreme situations.

[0041] The overall concept of the solution provided by the embodiments of this application has been introduced above. The specific implementation methods of the embodiments of this application will be introduced from various aspects below.

[0042] The following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application are applicable. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0043] See Figure 1 This is a schematic diagram of a possible application scenario provided by an embodiment of this application. In this scenario, a terminal device 101 and a server 102 may be included.

[0044] Terminal device 101 can be a mobile phone, tablet computer (PAD), personal computer (PC), wearable device, vehicle terminal, etc. Server 102 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms.

[0045] Terminal device 101 and server 102 can communicate directly or indirectly through one or more communication networks 103. The communication network 103 can be a wired network or a wireless network. For example, the wireless network can be a mobile cellular network or a Wireless-Fidelity (WIFI) network. Of course, it can also be other possible networks, and this embodiment of the invention does not limit them.

[0046] It should be noted that the data processing method in this embodiment can be executed by a computer device, which can be a terminal device 101 or a server 102, or both terminal device 101 and server 102 can be used together. For example, when a user or customer service representative uses their respective terminal device to input data, the intelligent response system in the terminal device can utilize the terminal device's own computing resources to complete the aforementioned data processing method. As another example, when the aforementioned data processing method is jointly completed by the server and terminal devices, after a user or customer service representative inputs corresponding data on the terminal device, the server can obtain the corresponding input data from these terminal devices and perform the corresponding data processing method.

[0047] It should be understood that Figure 1 The examples shown are merely illustrative; in reality, the number of terminal devices and servers, as well as the communication methods, are not limited and are not specifically restricted in the embodiments of this application.

[0048] See Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application. For ease of explanation, as shown below... Figure 2 The data processing method illustrated is applied in a scenario where both users and human customer service representatives input data using terminal devices, and the data processing method is executed through a server that communicates with each terminal device. For example... Figure 2 As shown, the specific implementation steps of this method are as follows:

[0049] Step S201: Obtain the input data received by the intelligent response system. The input data includes: input data from the questioner and input data from the human responder.

[0050] First, it should be clarified that the above... Figure 2 The method shown is a data processing approach applied to an intelligent response system, which includes both machine-based and human-based response modes. When a user enters the intelligent response system and raises a question, the machine-based response module is triggered first. If the user's question remains unresolved after a certain period, or if the user actively requests access to human customer service, the intelligent response system will trigger the corresponding human-based response module, allowing a human customer service representative to connect to the system and respond to the user's question.

[0051] Therefore, when step S201 is executed, there are already two parties in the intelligent response system, and both parties have made corresponding data inputs. So, when the server obtains the input data received by the intelligent response system during step S201, it will include the input data from the questioner (i.e., the user) and the input data from the human responder (i.e., the human customer service representative).

[0052] Step S202: Based on a preset set of keywords, perform keyword detection on the input data to obtain the corresponding target detection results.

[0053] The target detection result includes the overall distribution information of the target key data in the keyword set within the aforementioned input data. Optionally, this overall distribution information may include: the frequency of occurrence of the target key data, the source information of the target key data, the order in which the target key data appears, and the intensity level of the target key data itself.

[0054] After the server obtains the input data from the questioner and the human responder through step S201, it needs to perform keyword detection on the obtained input data according to the preset keyword set.

[0055] Optionally, during the detection process, the server can perform keyword detection within different time ranges for different sources. When performing keyword detection for human responders, the detection time range is from the time the human responder accesses the intelligent response system and begins interacting with the corresponding questioner until the current moment. When performing keyword detection for questioners, the server needs to perform keyword detection on all input data from the time the questioner first accesses the intelligent question-and-answer system within a certain time range until the current moment. The specific time range can be defined by the user according to their own needs in practical applications; this application does not require it.

[0056] For example, suppose that at 10:00 AM on February 2, 2020, the questioner first accesses the intelligent response system. During this time, the questioner does not choose human response but interacts with the machine response for a period of time. At 11:00 AM, the questioner accesses the intelligent response system for the second time. This time, the questioner chooses human response and interacts with the human responder for a period of time. Then, when the server performs keyword detection, the keyword detection time range for the questioner's input data is from 10:00 AM to the current time, while the keyword detection time range for the human responder's input data is from 11:00 AM to the current time.

[0057] When performing keyword detection on input data, the server bases its operation on a preset keyword set. This keyword set contains at least one target key data element. During keyword detection, the server determines whether the input data contains the same target key data element based on this set. Therefore, in the data processing method proposed in this application embodiment, the server only needs to determine whether the input data contains characters identical to the target key data element, without needing to perform semantic analysis on each statement in the input data. This speeds up the server's response to the target key data element and avoids the computational resource consumption associated with semantic analysis.

[0058] For obtaining this important data, the server can use the following methods:

[0059] See Figure 3 The flowchart below shows a method for obtaining a keyword set according to an embodiment of this application. Figure 3 As shown, the specific implementation steps of this method are as follows:

[0060] Step S301: Obtain at least one keyword.

[0061] In the step of acquiring keywords, the server can use different methods to complete the acquisition. For example, the server can acquire the keywords entered by the service provider corresponding to the intelligent response system, or it can acquire the keywords marked by human customer service during data interaction, or it can acquire the corresponding keywords from different databases through the network, etc. This application does not limit this.

[0062] Step S302: Convert at least one keyword obtained according to a preset format to obtain the corresponding target key data, and store the target key data in the keyword set.

[0063] After acquiring at least one keyword, the server needs to perform corresponding format conversion on these keywords so that each keyword can be stored in the keyword set in a unified and standard format.

[0064] For example, the results of step S302 above will be illustrated below using a keyword set as a data table.

[0065] Table 1

[0066]

[0067] As shown in Table 1, when the server retrieves keywords, it obtains words such as X and Y from the "Word Name" column. When the server performs format conversion, it generates corresponding primary key IDs, system IDs, etc., where the source ID indicates the different service providers corresponding to the keywords. It's important to clarify that since the same intelligent response system may not be used by only one service provider, for a keyword set, keywords from different service providers need to be identified with corresponding source IDs for use by users and customer service representatives of different service providers. The "Word Type" column represents the different types of keywords; for example, 1 indicates a profanity, 2 indicates a sensitive word, etc. The "Word Expansion" column indicates similar word extensions and other expressions related to the word.

[0068] The above describes how to obtain the keyword set and how to perform keyword detection on the input data based on the keyword set. After completing the keyword detection, the server can perform the following operations:

[0069] Step S203: If, based on the target detection results, it is determined that there is key target data in the input data, then the order in which the key target data appears is obtained based on the overall distribution information.

[0070] After completing the detection of the input data and obtaining the corresponding target detection results, the server can judge the target detection results to determine whether the target key data in the aforementioned keyword set exists in the input data. If it is determined that the target key data exists in the input data, the server obtains the order in which the target key data appears in all the input data based on the overall distribution information included in the target detection results.

[0071] Step S204: Based on the above order of appearance and combined with the preset set of response data, output the corresponding target response data to the source of the input data respectively.

[0072] Specifically, after obtaining the order of appearance, the server can select the corresponding target response data from the response data set based on the different order of appearance of the target key data, and then output the corresponding target response data to the source of the input data.

[0073] For example, assuming the target key data appears first in the input data from the questioner, the server can select the corresponding target response data, such as "Please don't be angry, I will try my best to answer your question," from the response data set and output this target response data to the questioner. Simultaneously, based on the content of the response data set, the server will also output "Please don't be angry, I suggest you deal with this situation rationally" to the human responder. Thus, in the same scenario, different target response data is output to both parties from the data source.

[0074] For example, assuming the target key data appears first in the input data from the human responder, the server also needs to select the corresponding target response data from the response data set. For instance, when facing a human responder, the server can output target response data such as "Please use language correctly," while when facing the person asking the question, the server can output target response data such as "Please don't be angry" or "You can choose to change to a human customer service representative."

[0075] In this way, the server can choose different target response data when facing different situations, and respond with different target response data for different data sources. This can effectively alleviate the problem of poor user experience caused by the emotional fluctuations of both parties in the intelligent response process, as well as the problem of low efficiency in question resolution due to emotional issues.

[0076] The above describes the detailed steps of data processing by the server during the data interaction between the questioner and the human responder in the intelligent response process. The following will introduce the data processing methods that the server can perform before and after this process.

[0077] Optionally, when the server executes step S204, in addition to retrieving the corresponding target response data from a preset response data set according to the order of appearance, the server may also perform the following operations to complete the acquisition of the target data.

[0078] See Figure 4 The flowchart below shows a method for outputting target response data provided in an embodiment of this application. Figure 4 As shown, the specific implementation steps of this method are as follows:

[0079] Step S401: Based on the overall distribution information, obtain the cumulative number of times the target key data appears in one side of the input data within a preset time range;

[0080] Step S402: Based on the order of appearance and the cumulative number of times, retrieve the target response data corresponding to the order of appearance and the cumulative number of times from the response data set, and output the target response data to the source.

[0081] After performing keyword detection, the server can obtain the cumulative number of times the target key data appears in one input data within a preset time range from the overall distribution information included in the target detection results.

[0082] For example, taking input data from the questioner as an example, based on the overall distribution information, the cumulative number of times the target key data appears in the questioner's input data within a day is obtained. Then, based on the order of appearance included in the overall distribution information, the target response data is obtained from the response data set.

[0083] As shown in Table 2, this table illustrates the different response data that should be output to the questioner for different cumulative occurrences of the target key data when it first appears in the questioner's input data.

[0084] Table 2

[0085]

[0086]

[0087] From Table 2 above, the server can select the corresponding target response data to output to the questioner, thereby providing appropriate emotional reassurance.

[0088] It should be noted that, taking Table 2 above as an example, the response data set may also include: 1. Target key data, which is the different response data that should be output to the questioner for different cumulative counts in the questioner's input data when the target key data first appears in the questioner's input data; 2. Target key data, which is the different response data that should be output to the human responder for different cumulative counts in the human responder's input data when the target key data first appears in the questioner's input data; 3. Target key data, which is the different response data that should be output to the human responder for different cumulative counts in the human responder's input data when the target key data first appears in the human responder's input data, as shown in Table 3.

[0089] Table 3

[0090] Cumulative number of times degree Reply data 1 Mild Please use language correctly. 2 moderate Please treat every user with care. 3 times or more Severe You seem agitated; you might need to rest.

[0091] The above describes the corresponding data processing methods that the server can perform on the target detection results of keyword detection when there is data interaction between the two parties in the intelligent response system.

[0092] When only the questioner inputs data in the intelligent response system (in other words, when the questioner is using the machine response module), the server can also perform the following operations:

[0093] See Figure 5 This is a flowchart illustrating a method for assigning emotion tags according to an embodiment of this application. Figure 5 As shown, the specific implementation steps of this method are as follows:

[0094] Step S501: Obtain the target number of times the target key data appears in the input data within a preset time range;

[0095] The preset time range can be the same as described above. Figure 4 The preset time ranges shown are the same, for example, all within 24 hours, or all from 0:00 of the day until the current time. This application does not impose any restrictions on this.

[0096] Step S502: Based on the target number of times, associate the questioner with the corresponding sentiment tag.

[0097] At this point, the server obtains the target frequency from the input data of the questioner. Therefore, the server can associate the sentiment label corresponding to that target frequency with the questioner. For example, as shown in Tables 2 and 3, when the target key data appears once, it can be marked as mild; when the target key data appears three or more times, it can be marked as severe. In this case, mild, moderate, severe, etc., can be used as the corresponding sentiment labels.

[0098] On the other hand, when the server associates the corresponding sentiment tag with the questioner, it can also simultaneously output corresponding response data to the questioner based on the target number of responses. Furthermore, the response data can be obtained from the response data set shown in Table 2, corresponding to the target number of responses.

[0099] Step S503: Before the human responder accesses the intelligent response system, send the emotion tag associated with the questioner to the human responder.

[0100] Specifically, before the human responder needs to access the intelligent response system, the server can send the aforementioned emotion tags assigned to the questioner to the human responder, so that the human responder can obtain the emotion assessment results of the questioner they are about to face in advance, making it easier for them to adjust their response status accordingly. In this way, the user experience of both parties can be improved simultaneously.

[0101] After the server completes the real-time detection of the input data in the intelligent response system and the questioner ends the response service, the server can also archive the response service.

[0102] Optionally, during data archiving, the server needs to select input data from the input data originating from the problem initiator that does not contain the target key data as the target input data and save this target input data to a preset storage address. On the other hand, the server also needs to save all input data from the human respondent to the preset storage address. In this way, filtering the data from the problem initiator before storing it can avoid storing the target key data, reduce the probability of storing dirty data in the database, and reduce the pressure on maintenance personnel to collect statistics. On the other hand, storing all data from the human respondent can facilitate the corresponding evaluation of the human respondent and provide them with a data foundation.

[0103] The above is an introduction to a data processing method provided by an embodiment of this application. It should be understood that the above method and various embodiments can be implemented through different combinations. For ease of understanding, the above method will be described below through specific business scenarios.

[0104] See Figure 6 This is a logical schematic diagram of a data processing method provided in an embodiment of this application, such as... Figure 6As shown, in the intelligent response system that applies the above data processing method, when a user (i.e., the questioner) begins using the system, the machine response module first registers a corresponding robot based on the user's specific business needs. This ensures that the user receives a targeted answer. After the intelligent response system completes robot registration, it can proceed with the corresponding chat and Q&A phase based on the user's question. During this phase, the server can perform keyword detection on the user's input data. When target key data is detected, the server assigns a corresponding emotion tag to the user based on the target frequency of the target key data. Furthermore, when the user chooses to connect to a human agent, the emotion tag can be sent to the human agent before they connect to the intelligent response system.

[0105] Once the interaction between the user and human customer service begins, the server can perform keyword detection on the input data from both sides. After detecting the target key data, the server will output the corresponding response data to the human customer service representative and the user respectively.

[0106] After the user ends the chat, the server can also archive and store the input data of the user and the human customer service separately. That is, the target input data that does not contain the target key data in the user's input data is stored in a preset address, and all the input data of the human customer service is stored in a preset address.

[0107] Based on the same inventive concept, embodiments of this application also provide a statistical information collection device.

[0108] See Figure 7 This application provides a statistical information collection device, which may be the aforementioned terminal device or a chip or integrated circuit in the device. The device includes modules / units / technical means for executing the method executed by the terminal device in the above method embodiments.

[0109] For example, the device 700 includes:

[0110] The acquisition module 701 is used to acquire the input data received by the intelligent response system; wherein, the input data includes: input data from the questioner and input data from the human responder;

[0111] Processing module 702 is used to perform keyword detection on the input data based on a preset keyword set to obtain corresponding target detection results; wherein, the target detection results include: the overall distribution information of target key data in the keyword set in the input data; if it is determined based on the target detection results that the target key data exists in the input data, then the order of appearance of the target key data is obtained based on the overall distribution information;

[0112] The output module 703 is used to output the corresponding target response data to the source of the input data based on the order of appearance and in combination with a preset set of response data.

[0113] Optionally, when the output module 703 outputs corresponding target response data to the source of the input data based on the order of occurrence and in combination with a preset response data set, it is specifically used to: obtain the cumulative number of times the target key data appears in one party's input data within a preset time range based on the overall distribution information; obtain the target response data corresponding to the order of occurrence and the cumulative number of occurrences from the response data set based on the order of occurrence and the cumulative number of occurrences, and output the target response data to the source party.

[0114] Optionally, the device further includes a storage module 704. After the output module outputs the corresponding target response data to the source of the input data, the storage module is configured to: select input data from the input data from the questioner that does not contain the target key data as target input data and save the target input data to a preset storage address; and save all the input data from the human responder to the preset storage address.

[0115] Optionally, when the input data only contains input data from the questioner, the processing module 702 is further configured to: obtain the target number of times the target key data appears in the input data within a preset time range; associate the questioner with the corresponding emotion tag based on the target number of times; and send the emotion tag associated with the questioner to the human responder before the human responder accesses the intelligent response system.

[0116] Optionally, before acquiring the input data received by the intelligent response system, the acquisition module 701 is further configured to: acquire at least one keyword; convert the at least one keyword according to a preset format to obtain corresponding target key data, and store the target key data in the keyword set.

[0117] As one example, Figure 7 The device described can be used to perform Figure 2 The method described in the illustrated embodiment is therefore relevant to the functions that each functional module of the device can achieve. Figure 2 The description of the embodiments shown will not be repeated here.

[0118] It should be noted that although several modules or sub-modules of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units described above can be embodied in a single module. Conversely, the features and functions of a module described above can be further divided and embodied by multiple modules.

[0119] As one possible product form of the aforementioned device, see [link to product description]. Figure 8 This application also provides an electronic device 800, comprising:

[0120] At least one processor 801; and a communication interface 803 communicatively connected to the at least one processor 801; the at least one processor 801 causes the electronic device 800 to execute the method steps performed by any device in the above method embodiments through the communication interface 803 by executing instructions stored in the memory 802.

[0121] Optionally, the memory 802 is located outside the electronic device 800.

[0122] Optionally, the electronic device 800 includes the memory 802, which is connected to the at least one processor 801, and stores instructions executable by the at least one processor 801. (Appendix) Figure 8 The dashed line indicates that memory 802 is optional for electronic device 800.

[0123] The processor 801 and the memory 802 can be coupled through an interface circuit or integrated together; no restriction is imposed here.

[0124] This application embodiment does not limit the specific connection medium between the processor 801, memory 802, and communication interface 803. This application embodiment... Figure 8 The processor 801, memory 802, and communication interface 803 are connected via a bus 804. Figure 8 The connections between other components are shown in bold and are for illustrative purposes only, not as limiting information. The bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, Figure 8 The text uses only a single thick line to represent a bus, but this does not imply that there is only one bus or one type of bus. It should be understood that the processor mentioned in the embodiments of this application can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0125] For example, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0126] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. 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 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), Synchlink DRAM (SLDRAM), and Direct RAM (DR RAM).

[0127] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0128] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0129] As another possible product form, this application embodiment also provides a computer-readable storage medium for storing instructions that, when executed, cause a computer to perform the method steps performed by any of the devices in the above method examples.

[0130] As another possible product form, this application embodiment also provides a computer program product containing instructions, wherein the computer program product stores instructions that, when run on a computer, cause the computer to execute the method steps performed by any device in the above method embodiments.

[0131] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A data processing method, characterized in that, Applied to an intelligent response system, which includes machine response and human response, the method includes: The system acquires input data received by the intelligent response system; wherein the input data includes: input data from the questioner and input data from the human responder. Based on a preset set of keywords, and combined with a time range determined by the questioner and a time range determined by the human responder, keyword detection is performed on the input data to obtain corresponding target detection results; wherein, the target detection results include: the overall distribution information of target key data in the keyword set in the input data; If, based on the target detection results, it is determined that the target key data exists in the input data, then, based on the overall distribution information, the order in which the target key data appears is obtained; Based on the order of appearance and combined with a preset set of response data, corresponding target response data are output to the questioner and the human responder, respectively. Wherein, when the input data only contains input data from the questioner, the target number of times the target key data appears in the input data within a preset time range is obtained; Based on the target number of times, the questioner will be associated with the corresponding sentiment tag; Before the human responder connects to the intelligent response system, the emotion tag associated with the questioner is sent to the human responder.

2. The method as described in claim 1, characterized in that, Based on the order of appearance and combined with a preset set of response data, the system outputs corresponding target response data to both the questioner and the human responder, including: Based on the overall distribution information, the cumulative number of times the target key data appears in one side of the input data within a preset time range is obtained; Based on the order of appearance and the cumulative number of times, target response data corresponding to the order of appearance and the cumulative number of times are obtained from the response data set, and the corresponding target response data are output to the questioner and the human responder respectively.

3. The method as described in claim 1, characterized in that, After outputting the corresponding target response data to both the questioner and the human responder, the method further includes: From the input data originating from the questioner, select the input data that does not contain the target key data as the target input data, and save the target input data to a preset storage address; All input data from the human responder is saved to the preset storage address.

4. The method as described in claim 1, characterized in that, Before acquiring the input data received by the intelligent response system, the method further includes: Obtain at least one keyword; The at least one keyword is converted according to a preset format to obtain the corresponding target key data, and the target key data is stored in the keyword set.

5. A data processing apparatus, characterized in that, Applied to an intelligent response system, the intelligent response system including machine response and human response, the device includes: The acquisition module is used to acquire the input data received by the intelligent response system; wherein, the input data includes: input data from the questioner and input data from the human responder; The processing module is used to perform keyword detection on the input data based on a preset keyword set, combined with a time range determined by the questioner and a time range determined by the human responder, to obtain corresponding target detection results; wherein, the target detection results include: the overall distribution information of target key data in the keyword set in the input data; if it is determined based on the target detection results that the target key data exists in the input data, then the order of appearance of the target key data is obtained based on the overall distribution information; The output module is used to output the corresponding target response data to the questioner and the human responder respectively, based on the order of appearance and in combination with a preset set of response data; When the input data contains only input data from the questioner, the processing module is further configured to: obtain the target number of times the target key data appears in the input data within a preset time range; associate the questioner with the corresponding emotion tag based on the target number; and send the emotion tag associated with the questioner to the human responder before the human responder accesses the intelligent response system.

6. The apparatus as claimed in claim 5, characterized in that, The output module, based on the order of appearance and in conjunction with a preset set of response data, outputs corresponding target response data to both the questioner and the human responder. Specifically, it is used for: Based on the overall distribution information, the cumulative number of times the target key data appears in one side of the input data within a preset time range is obtained; Based on the order of appearance and the cumulative number of times, target response data corresponding to the order of appearance and the cumulative number of times are obtained from the response data set, and the corresponding target response data are output to the questioner and the human responder respectively.

7. The apparatus as claimed in claim 5, characterized in that, The device further includes a storage module, which, after the output module outputs the corresponding target response data to the questioner and the human responder respectively, is used for: From the input data originating from the questioner, select the input data that does not contain the target key data as the target input data, and save the target input data to a preset storage address; All input data from the human responder is saved to the preset storage address.

8. The apparatus as claimed in claim 5, characterized in that, Before acquiring the input data received by the intelligent response system, the acquisition module is further configured to: Obtain at least one keyword; The at least one keyword is converted according to a preset format to obtain the corresponding target key data, and the target key data is stored in the keyword set.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which executes the instructions stored in the memory to perform the method as described in any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store instructions that, when executed, cause the method as described in any one of claims 1-4 to be implemented.

11. A computer program product containing instructions, characterized in that, The computer program product stores instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1-4.

Images