Information processing method and device, equipment, medium and product

Abstract

The invention provides an information processing method and device, equipment, a medium and a product, the method is applied to a client, and the method comprises the following steps: in response to a sending request of first information, determining a processing judgment result of the first information; in response to the processing judgment result, indicating to process the first information, and sending the first information to an information processing server; and receiving reply information of the first information returned by the information processing server. In the method, a process of judging whether first information needs to be processed or not is added in a client aiming at a scene that a client and a digital assistant server carry out man-machine conversation, and when a processing judgment result indicates that the first information needs to be processed, an information processing server is called to carry out information processing. Thus, on the premise that the information processing requirement is met, the number of requests for the information processing server side is greatly reduced, and the resource use efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information processing method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] With the continuous development of computer technology, digital assistants have emerged. Digital assistants usually have natural language processing capabilities, and users can interact with digital assistants in the form of human-computer dialogue. Specifically, digital assistants can receive information input by users through the client, and generate reply information based on the information input by the user to complete a round of dialogue.

[0003] During the human-computer dialogue, the information input by the user will be transmitted to the digital assistant server. Considering that the information input by the user may contain key information that is not desired to be transmitted to the digital assistant server, it is usually possible to access the information processing server to process the information input by the user to avoid the key information from being transmitted to the digital assistant server.

[0004] However, in the above method, the client needs to frequently request the information processing server to process the information, which results in high transmission and storage costs, resulting in a certain degree of resource waste. Summary of the invention

[0005] The present application provides an information processing method. The method reduces the number of requests to the information processing server and improves resource utilization efficiency while meeting the information processing requirements. The present application also provides a device, an electronic device, a computer-readable storage medium, and a computer program product corresponding to the above method.

[0006] In a first aspect, the present application provides an information processing method, applied to a client, the method comprising:

[0007] In response to a request to send first information, determining a processing judgment result of the first information; wherein the first information represents natural language content, the sending request is used to trigger interaction with a digital assistant server, and the processing judgment result indicates whether to process the first information;

[0008] In response to the processing judgment result indicating that the first information is to be processed, the first information is sent to an information processing server; wherein the information processing server is used to process the first information into second information, the first information includes key information, and the second information does not include the key information;

[0009] Receive reply information for the first information returned by the information processing server, where the reply information for the first information is determined based on information generated after the digital assistant server performs natural language processing on the second information.

[0010] In some possible implementations, determining a result of processing and judging the first information includes:

[0011] A processing and judgment result of the first information is determined according to a key information identification result of the first information or a source scenario of the first information; wherein the key information identification result indicates whether the first information includes key information.

[0012] In some possible implementations, determining the processing and judgment result of the first information according to the key information identification result of the first information or the source scenario of the first information includes:

[0013] In response to the first information including key information, or the source scenario of the first information requires information processing, it is determined that the processing judgment result of the first information indicates that the first information is to be processed.

[0014] In some possible implementations, the method further includes:

[0015] In response to the processing determination result indicating that the first information is not to be processed, sending the first information to the digital assistant server;

[0016] Receive reply information for the first information returned by the digital assistant server.

[0017] In a second aspect, the present application provides an information processing method, which is applied to an information processing server, and the method comprises:

[0018] Receiving first information sent by a client, where the first information represents natural language content;

[0019] Processing the first information into second information, where the second information does not include key information in the first information;

[0020] Sending the second information to the digital assistant server, and receiving information generated by the digital assistant server after performing natural language processing on the second information; wherein the information generated after performing natural language processing on the second information is generated based on the language model called by the digital assistant server;

[0021] Determine reply information for the first information based on information generated after the digital assistant server performs natural language processing on the second information, and send the reply information for the first information to the client.

[0022] In some possible implementations, processing the first information into second information includes:

[0023] Identifying key information in the first information and a location of the key information;

[0024] The key information is processed according to the position of the key information to generate second information that does not include the key information.

[0025] In some possible implementations, processing the first information into second information includes:

[0026] determining, according to the task type represented by the first information, an information processing strategy for the first information;

[0027] According to the information processing strategy, the first information is processed into second information.

[0028] In some possible implementations, determining the information processing strategy of the first information according to the task type represented by the first information includes:

[0029] Sending the first information to a task type recognition model, and receiving the task type returned by the task type recognition model; wherein the task type recognition model is used to classify natural language processing tasks;

[0030] An information processing strategy for the first information is determined according to the task type.

[0031] In some possible implementations, the information processing strategy includes at least one of the following:

[0032] A strategy for replacing the key information with set characters;

[0033] strategies to hide said critical information;

[0034] Generate a replacement token based on the key information, and replace the key information with a strategy for the replacement token;

[0035] A policy for replacing the key information with setting information matching the key information type.

[0036] In some possible implementations, determining reply information for the first information according to information generated after the digital assistant server performs natural language processing on the second information includes:

[0037] Identify information that is identical to the second information in information generated by the digital assistant server after performing natural language processing on the second information;

[0038] Replacing the same information in the information generated by the digital assistant server after performing natural language processing on the second information with the key information in the first information respectively;

[0039] Determine reply information for the first information based on information generated by the replaced digital assistant server after natural language processing of the second information.

[0040] In a third aspect, the present application provides an information processing device, which is deployed on a client, and the device includes:

[0041] A determination module, configured to determine a processing judgment result of the first information in response to a sending request of the first information; wherein the first information represents natural language content, the sending request is used to trigger interaction with the digital assistant server, and the processing judgment result indicates whether to process the first information;

[0042] a communication module, configured to process the first information in response to the processing judgment result indicating that the first information is processed, and send the first information to an information processing server; wherein the information processing server is configured to process the first information into second information, the first information includes key information, and the second information does not include the key information;

[0043] The communication module is also used to receive reply information of the first information returned by the information processing server, and the reply information of the first information is determined based on information generated after the digital assistant server performs natural language processing on the second information.

[0044] In some possible implementations, the determining module is specifically configured to:

[0045] A processing and judgment result of the first information is determined according to a key information identification result of the first information or a source scenario of the first information; wherein the key information identification result indicates whether the first information includes key information.

[0046] In some possible implementations, the determining module is specifically configured to:

[0047] In response to the first information including key information, or the source scenario of the first information requires information processing, it is determined that the processing judgment result of the first information indicates that the first information is to be processed.

[0048] In some possible implementations, the communication module is further configured to:

[0049] In response to the processing determination result indicating that the first information is not to be processed, sending the first information to the digital assistant server;

[0050] Receive reply information for the first information returned by the digital assistant server.

[0051] In a fourth aspect, the present application provides an information processing device, which is deployed on an information processing server, and the device includes:

[0052] A communication module, configured to receive first information sent by a client, wherein the first information represents natural language content;

[0053] a processing module, configured to process the first information into second information, wherein the second information does not include key information in the first information;

[0054] The communication module is further used to send the second information to the digital assistant server, and receive information generated by the digital assistant server after performing natural language processing on the second information; wherein the information generated after performing natural language processing on the second information is generated based on the language model called by the digital assistant server;

[0055] The communication module is also used to determine reply information of the first information based on information generated after the digital assistant server performs natural language processing on the second information, and send the reply information of the first information to the client.

[0056] In some possible implementations, the processing module is specifically configured to:

[0057] Identifying key information in the first information and a location of the key information;

[0058] The key information is processed according to the position of the key information to generate second information that does not include the key information.

[0059] In some possible implementations, the processing module is specifically configured to:

[0060] determining, according to the task type represented by the first information, an information processing strategy for the first information;

[0061] According to the information processing strategy, the first information is processed into second information.

[0062] In some possible implementations, the processing module is specifically configured to:

[0063] Sending the first information to a task type recognition model, and receiving the task type returned by the task type recognition model; wherein the task type recognition model is used to classify natural language processing tasks;

[0064] An information processing strategy for the first information is determined according to the task type.

[0065] In some possible implementations, the information processing strategy includes at least one of the following:

[0066] A strategy for replacing the key information with set characters;

[0067] strategies to hide said critical information;

[0068] Generate a replacement token based on the key information, and replace the key information with a strategy for the replacement token;

[0069] A policy for replacing the key information with setting information matching the key information type.

[0070] In some possible implementations, the communication module is specifically used to:

[0071] Identify information that is identical to the second information in information generated by the digital assistant server after performing natural language processing on the second information;

[0072] Replacing the same information in the information generated by the digital assistant server after performing natural language processing on the second information with the key information in the first information;

[0073] Determine reply information for the first information based on information generated by the replaced digital assistant server after natural language processing of the second information.

[0074] In a fifth aspect, the present application provides an electronic device, comprising a processor and a memory. The processor and the memory communicate with each other. The processor is used to execute instructions stored in the memory so that the electronic device performs the information processing method in the first aspect or any implementation of the first aspect, or performs the information processing method in the second aspect or any implementation of the second aspect.

[0075] In a sixth aspect, the present application provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, wherein the instructions instruct an electronic device to execute the information processing method described in the first aspect or any one of the implementations of the first aspect, or to execute the information processing method in the second aspect or any one of the implementations of the second aspect.

[0076] In the seventh aspect, the present application provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the information processing method described in the first aspect or any one of the implementations of the first aspect, or to execute the information processing method described in the second aspect or any one of the implementations of the second aspect.

[0077] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.

[0078] It can be seen from the above technical solutions that this application has the following advantages:

[0079] The present application provides an information processing method, which is applied to a client. In response to a request to send first information, the client determines a processing judgment result of the first information, wherein the first information represents natural language content, the sending request is used to trigger interaction with a digital assistant server, and the processing judgment result indicates whether to process the first information. Then, in response to the processing judgment result indicating that the first information is to be processed, the client sends the first information to an information processing server, wherein the information processing server is used to process the first information into second information, the first information includes key information, and the second information does not include key information. The client receives reply information of the first information returned by the information processing server, and the reply information of the first information is determined based on information generated after the digital assistant server performs natural language processing on the second information.

[0080] In this method, for the scenario of human-computer dialogue between the client and the digital assistant server, a process of judging whether the first information needs to be processed is added in the client, and when the processing judgment result indicates that the first information needs to be processed, the information processing server is called to process the information. In this way, the number of requests to the information processing server is greatly reduced while meeting the information processing requirements, and the resource utilization efficiency is improved.

[0081] The present application also provides an information processing method, which is applied to an information processing server, receiving first information sent by a client, wherein the first information represents natural language content, processing the first information into second information, and the second information does not include key information in the first information, then sending the second information to a digital assistant server, receiving information generated by the digital assistant server after natural language processing of the second information, wherein the information generated after natural language processing of the second information is generated based on the digital assistant server calling a language model, determining reply information for the first information based on the information generated after natural language processing of the second information by the digital assistant server, and sending the reply information for the first information to the client.

[0082] In this method, the information processing server can process the first information sent by the client, generate the second information that does not include the key information, and then call the digital assistant server to process the second information, and finally determine the reply information of the first information. In this way, through the information processing process, the key information is prevented from being transmitted to the digital assistant server, and the information processing requirements are met. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings required for use in the embodiments are briefly introduced below.

[0084] Figure 1A and Figure 1B A schematic diagram of the architecture of an information processing system provided in an embodiment of the present application;

[0085] Figure 2 A flowchart of an information processing method provided in an embodiment of the present application;

[0086] Figure 3 A flowchart of another information processing method provided in an embodiment of the present application;

[0087] Figure 4 A flowchart of another information processing method provided in an embodiment of the present application;

[0088] Figure 5 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application;

[0089] Figure 6 A schematic diagram of the structure of another information processing device provided in an embodiment of the present application;

[0090] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0091] The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0092] First, some technical terms involved in the embodiments of the present application are introduced.

[0093] Digital assistants, also known as conversational robots, usually have natural language processing capabilities. In some examples, users can interact with digital assistants through human-computer dialogue. For example, users can enter questions related to general knowledge, and the digital assistant generates responses to questions related to general knowledge by analyzing the content entered by the user, thereby completing a round of dialogue. In other examples, the digital assistant can process natural language content according to the needs of the user. For example, the user can enter a text and instruct the digital assistant to perform relevant processing (such as text summarization). The digital assistant identifies the user's needs, summarizes the text entered by the user, and generates text summary content, thereby completing a round of dialogue.

[0094] Based on the above human-computer dialogue scenario, it can be known that after the user enters information on the client, the information entered by the user will be transmitted to the digital assistant server. In some examples, the information entered by the user may include key information, where key information may refer to information that is not desired to be transmitted to the digital assistant server, for example, key information may be information related to personal attributes.

[0095] In the related technology, an information processing server can be connected to process the information input by the user to prevent key information from being transmitted to the digital assistant server. However, in the above method, the client needs to frequently request the information processing server to process the information, which has high transmission and storage costs, resulting in a certain degree of resource waste.

[0096] In view of this, the present application provides an information processing method. The method is applied to a client, and in response to a request to send a first message, the client determines a processing judgment result of the first message, wherein the first message represents natural language content, and the sending request is used to trigger interaction with a digital assistant server, and the processing judgment result indicates whether to process the first message, and then, in response to the processing judgment result indicating that the first message is to be processed, the client sends the first message to an information processing server, wherein the information processing server is used to process the first message into second information, the first message includes key information, and the second message does not include key information, and the client receives reply information of the first message returned by the information processing server, and the reply information of the first message is determined based on information generated after the digital assistant server performs natural language processing on the second message.

[0097] In this method, for the scenario of human-computer dialogue between the client and the digital assistant server, a process of determining whether the first information needs to be processed is added to the client, and when the processing determination result indicates that the first information needs to be processed, the information processing server is called to process the information. In this way, the number of requests to the information processing server is reduced while meeting the information processing requirements, thereby improving resource utilization efficiency.

[0098] To facilitate understanding of the technical solution provided by the embodiments of the present application, it will be described below with reference to the accompanying drawings.

[0099] In this application, a client, a digital assistant server and an information processing server are involved. The system architecture of the information processing system will be introduced below.

[0100] See also Figure 1A As shown, an architectural diagram of an information processing system is shown, where the information processing system 100 includes a client 10, a digital assistant server 20 and an information processing server 30.

[0101] The client 10 is deployed on a terminal, for example, the client 10 can be deployed on a terminal such as a desktop, a laptop or a smart phone. The digital assistant server 20 is connected to the information processing server 30, and the digital assistant server 20 and the information processing server 30 are connected to the client 10 respectively.

[0102] Specifically, the client 10 is used to receive first information input by a user, the digital assistant server 20 is used to perform natural language processing on the first information and generate reply information, and the information processing server 30 is used to process the first information and generate second information that does not include key information.

[0103] In the embodiment of the present application, the digital assistant server 20 and the information processing server 30 are both independent software systems. That is, the digital assistant server 20 and the information processing server 30 independently provide human-computer dialogue services and information processing services. For example, the digital assistant server 20 and the information processing server 30 can provide human-computer dialogue services and information processing services in the form of cloud services, plug-ins, application software (application, APP), etc.

[0104] Since the client 10 is connected to the digital assistant server 20 and the information processing server 30 respectively, the client 10 can interact with the digital assistant server 20 to realize human-computer dialogue. The client 10 can also interact with the information processing server 30 to realize processing for the first information.

[0105] See also Figure 1B As shown in the schematic diagram of the architecture of an information processing system, the information processing system 100 also includes a business service end 40.

[0106] Among them, the client 10 is deployed on the terminal, the digital assistant server 20 and the information processing server 30 are respectively connected to the business server 40, and the business server 40 is connected to the client 10.

[0107] Similarly, the client 10 is used to receive first information input by a user, the digital assistant server 20 is used to perform natural language processing on the first information and generate reply information, and the information processing server 30 is used to process the first information and generate second information that does not include key information.

[0108] The business service end 40 is used to implement office automation (OA). In other words, the business service end 40 can be a server end of an OA system, a server end of a business platform, etc. The business service end 40 can provide a plurality of functional modules with different functions, such as an instant messaging module, a form module, a task management module, a conference module, a schedule module, etc.

[0109] In an embodiment of the present application, the digital assistant server 20 and the information processing server 30 are connected to the business service end 40, that is, the digital assistant server 20 and the information processing server 30 serve as functional modules of the business service end 40, providing human-computer dialogue services and information processing services in the OA system or business platform.

[0110] Since the client 10, the digital assistant server 20 and the information processing server 30 are all connected to the digital assistant server 20 and the information processing server 30, the client 10 can interact with the digital assistant server 20 through the business server 40 to achieve human-computer dialogue. The client 10 can also interact with the information processing server 30 through the business server 40 to achieve processing for the first information.

[0111] It should be noted that Figure 1B In the figure, the digital assistant server 20, the information processing server 30 and the business server 40 are taken as three server ends for illustration. In some possible implementations, the digital assistant server 20, the information processing server 30 and the business server 40 may also be integrated into one server end, and the integrated server end provides human-computer dialogue services and information processing services. The embodiments of the present application do not limit this.

[0112] Next, the information processing method provided by the present application is described in conjunction with the accompanying drawings. Figure 2 The flowchart of an information processing method provided in the embodiment of the present application is shown, and the method can be executed by a client, and the method specifically includes:

[0113] S201: In response to a request to send first information, determine a processing result of the first information.

[0114] The first information can be understood as information input by the user in the client for human-computer dialogue. For example, a dialogue window is displayed in the client, and the user can input the first information through the dialogue window. For another example, multiple controls are displayed in the client, and different controls correspond to different natural language processing tasks. The user can input the first information by selecting a control.

[0115] In the embodiment of the present application, the first information represents natural language content. In other words, the first information may be content input by a user in natural language, such as natural language content representing a certain question, or natural language content representing a certain natural language processing requirement.

[0116] The request to send the first message can be used to trigger interaction with the digital assistant server. Among them, the digital assistant server has natural language processing capabilities and can process different types of natural language processing tasks. In other words, the request to send the first message can be understood as calling the digital assistant server to perform natural language processing, and then generating a request for reply information.

[0117] The embodiment of the present application does not limit the triggering method of the request to send the first information. For example, the sending operation performed by the user after entering the first information in the client can trigger the request to send the first information. For another example, when the user enters the first information by selecting a control in the client, the user's selection operation on the control can trigger the request to send the first information.

[0118] The result of the first information processing judgment may indicate whether to process the first information. In other words, the result of the first information processing judgment may indicate that the first information needs to be processed or does not need to be processed.

[0119] In the embodiment of the present application, the fact that the first information does not need to be processed can be understood as two situations: the first information does not include key information, or the first information includes key information but the key information does not need to be processed.

[0120] Among them, key information can be understood as information that is not desired to be transmitted to the digital assistant server. For example, key information may include information related to personal attributes, information related to business data, etc. Key information may be different for different businesses, and users can set the scope of key data based on actual information processing needs.

[0121] like Figure 3 As shown, after receiving the first information, the client can respond to the request to send the first information and determine the processing result of the first information according to the key information identification result of the first information or the source scenario of the first information. The key information identification result indicates whether the first information includes key information.

[0122] In some possible implementations, a first key information identification model is deployed in the client, and the client can call the first key information identification model to perform key information identification on the first information, and determine the key information identification result of the first information, for example, whether it includes key information or does not include key information. The first key information identification model can be a pre-trained classification model for identifying key information. In other possible implementations, the client can also use regular expression matching to perform key information identification on the first information, and determine the key information identification result of the first information, for example, whether it includes key information or does not include key information.

[0123] The source scenario of the first information can be understood as the business scenario when the user inputs the first information. In some embodiments, the client may be a client of a business platform, and the business platform includes multiple functional modules that provide different functions. In this case, the source scenario of the first information may be the functional module that generates the first information. For example, when the user inputs the first information in the video conferencing module, the source scenario of the first information may be the video conferencing scenario, and when the user inputs the first information in the document module, the source scenario of the first information may be the document scenario.

[0124] In the embodiment of the present application, the user can configure in advance whether information processing is required for different business scenarios. In other words, for multiple functional modules provided by the business platform, the user can configure different functional modules to require information processing, or to configure them not to require information processing. In this way, flexible configuration is performed in combination with actual business scenarios to meet the information processing needs for key information in different business scenarios.

[0125] Specifically, in response to the first information including key information, or the source scenario of the first information requiring information processing, the client determines that the processing judgment result of the first information indicates that the first information is processed. Otherwise, the client determines that the processing judgment result of the first information indicates that the first information is not processed.

[0126] That is to say, when there is key information in the first information, or the business scenario in which the first information is located requires information processing, the processing judgment result may be that the first information needs to be processed. For other situations, the processing judgment result may be that the first information does not need to be processed.

[0127] In this way, before the client actually interacts with the digital assistant server, the client comprehensively judges whether the first information of this human-computer dialogue needs to be processed based on the first information's own content and source scenario. On the one hand, this avoids key information from being directly transmitted to the digital assistant server to meet information processing needs. On the other hand, it avoids the need to call the information processing server for information processing for all first information sending requests, thereby reducing the number of requests.

[0128] S202: In response to the processing judgment result indicating processing of the first information, the first information is sent to the information processing server.

[0129] In the embodiment of the present application, the information processing server is used to process the first information into the second information, and the first information includes key information, and the second information does not include key information. In other words, the information processing server can be understood as a server for processing key information, and the information processed by the information processing server does not contain key information.

[0130] When the processing judgment result indicates that the first information needs to be processed, the client sends the first information to the information processing server, and the information processing server processes the key information in the first information, removes the key information in the first information, and obtains the second information.

[0131] S203: Receive reply information of the first information returned by the information processing server.

[0132] In an embodiment of the present application, the reply information of the first information can be determined based on the information generated by the digital assistant server after performing natural language processing on the second information. Generally, the digital assistant server has the ability to call a language model, and the language model has the ability to understand natural language and can complete various types of natural language processing tasks. For example, the language model can be a deep learning model trained using text data.

[0133] In other words, after the information processing server processes the information, the information processing server can call the digital assistant server, the digital assistant server calls the language model to perform natural language processing on the second information to generate information, and the information processing server determines the reply information of the first information based on the information generated by the digital assistant server.

[0134] Then, the information processing server returns the reply information of the first information to the client, and after receiving the reply information of the first information, the client can present the reply information of the first information, for example, present the reply information of the first information in the dialogue page, thus completing a round of human-computer dialogue.

[0135] Furthermore, if Figure 3 As shown, in response to the processing judgment result indicating that the first information is not to be processed, the client can send the first information to the digital assistant server and receive reply information of the first information returned by the digital assistant server.

[0136] That is to say, when there is no key information in the first information, or when there is no need to process the key information in the first information, the client directly calls the digital assistant server without sending the first information to the information processing server, which then calls the digital assistant server. In this way, the number of data transmissions between the client and the server is reduced from the source.

[0137] In this method, for the scenario of human-computer dialogue between the client and the digital assistant server, a process of determining whether the first information needs to be processed is added to the client, and when the processing determination result indicates that the first information needs to be processed, the information processing server is called to process the information. In this way, the number of requests to the information processing server is reduced while meeting the information processing requirements, thereby improving resource utilization efficiency.

[0138] The foregoing describes the information processing method provided by the present application from the perspective of the client. The following will introduce the specific implementation process of information processing from the perspective of the information processing server.

[0139] See also Figure 4 The flowchart of an information processing method provided in the embodiment of the present application is shown, and the method can be executed by the information processing server. The method specifically includes:

[0140] S401: Receive first information sent by a client.

[0141] The first information represents natural language content. For example, the first information may be information input by a user in a natural language in a client and requiring natural language processing.

[0142] In the present application example, continue as Figure 3 As shown, the client first determines whether the first information needs to be processed. When the processing determination result of the first information indicates that the first information needs to be processed, the client sends the first information to the information processing server, and the information processing server receives the first information for subsequent processing of the first information.

[0143] S402: Process the first information into second information.

[0144] The second information does not include the key information in the first information. That is, the information processing server processes the key information in the first information without changing other information of the first information except the key information, and generates the second information that does not include the key information, thereby hiding the key information.

[0145] In a specific implementation, the information processing server may identify the key information and the position of the key information in the first information, and process the key information according to the position of the key information to generate the second information that does not include the key information.

[0146] In some possible implementations, a second key information identification model is deployed in the information processing server, and the information identification server can call the second key information identification model to perform key information identification on the first information, determine the key information included in the first information and the position of the key information in the first information (for example, the Nth to Mth characters in the first information).

[0147] The second key information recognition model may be a pre-trained classification model for recognizing key information. Compared with the first key information recognition model deployed in the client, since the information processing server has more computing resources, the volume and accuracy of the second key information recognition model deployed in the information processing server may be better than the first key information recognition model deployed in the client.

[0148] By identifying the key information in the first information and determining the position of the key information in the first information, the information processing server can locate the key information in the first information, process the key information, generate second information that does not include the key information, and complete the information processing.

[0149] In some embodiments, the information processing server can also process the first information through different information processing strategies. Specifically, the information processing server can determine the information processing strategy of the first information according to the task type represented by the first information, and process the first information into the second information according to the information processing strategy.

[0150] In some possible implementations, a task type identification model is deployed in the information processing server. The information processing server can send the first information to the task type identification model, receive the task type returned by the task type identification model, and determine the information processing strategy of the first information based on the task type.

[0151] In this way, the information identification server identifies the first information by calling the task type identification model to determine the task type represented by the first information. The task type identification model may be a pre-trained classification model for classifying natural language processing tasks.

[0152] In other words, the information processing server can combine the task type and use different information processing strategies to process information to meet business needs and improve the flexibility of information processing.

[0153] The task type represented by the first information can be understood as the task type of the natural language processing task indicated by the first information. For example, when the first information is "help me query the schedule of user A", the task type represented by the first information can be a query task. For another example, when the first information is "help me translate the content of document B", the task type represented by the first information can be a translation task.

[0154] It is understandable that different task types correspond to different natural language processing requirements, and for different task types, the key information plays different roles in the first information. For example, when the first information is "Help me check the schedule of user A", "user A" is the key information, and the key information of user A is necessary information in the process of natural language processing of the first information. For another example, when the first information is "Help me translate the content of document B", the name of the person in document B is the key information, and the name of the person in document B is non-essential information in the process of natural language processing of the first information.

[0155] Therefore, the embodiment of the present application is configured with different information processing strategies for different task types. In some possible implementations, the mapping relationship between the task type and the information processing strategy can be pre-configured. After determining the task type represented by the first information, the information processing strategy of the first information is determined based on the mapping relationship between the task type and the information processing strategy. In other words, considering that in actual business scenarios, different information processing strategies can have different information processing effects for different task types, therefore, the user can pre-configure information processing strategies with better information processing effects (such as faster information processing speed, better effect of natural language processing after information processing, etc.) in combination with the task type. For example, for translation tasks, the first type of information processing strategy is configured, and for query tasks, the second type of information processing strategy is configured, thereby improving the effect of information processing for different task types.

[0156] In this way, the information processing server can combine the task type and adopt a matching information processing strategy to process information, while avoiding transmitting key information to the digital assistant server and not affecting the accuracy of the subsequent natural language processing generated by the digital assistant server.

[0157] In an embodiment of the present application, the information processing strategy may include at least one of the following: a strategy for replacing key information with set characters, a strategy for hiding key information, a strategy for generating a replacement token based on key information, a strategy for replacing key information with a replacement token, and a strategy for replacing key information with set information that matches the key information type.

[0158] Among them, in the strategy of replacing the key information with the set characters, the set characters may be characters that do not represent the actual meaning, such as "*". For example, when the key information in the first information is a mobile phone number, some digits of the mobile phone number may be replaced with "*" so that the generated second information does not include the complete mobile phone number, that is, does not include the key information.

[0159] In the strategy of hiding key information, the information processing server can hide the key information. For example, when the key information in the first information is a mobile phone number, the mobile phone number is hidden so that the generated second information does not include the key information.

[0160] In the strategy of generating a replacement token based on key information and replacing the key information with the replacement token, the replacement token can be understood as content corresponding to the key information and used to replace the key information. For example, when the key information in the first information is the user name "Zhang XX", a replacement token "name-1" corresponding to "Zhang XX" can be generated, so that "name-1" represents "Zhang XX" in the generated second information, and does not include the complete user name, that is, does not include the key information.

[0161] In the strategy of replacing key information with setting information matching the key information type, the key information type may refer to the category of key information, such as mobile phone number, user name, etc. Corresponding setting information is configured for different key information types. For example, for the key information type of user name, the setting information may be "user Xiao Zhang", "user Xiao Li", etc. When the key information in the first information is the user name "Zhang XX", "Zhang XX" may be replaced with "user Xiao Zhang", so that the generated second information does not include the complete user name, that is, does not include the key information.

[0162] S403: Send the second information to the digital assistant server, and receive information generated by the digital assistant server after performing natural language processing on the second information.

[0163] After the information processing server completes information processing and processes the first information into second information that does not include key information, the information processing server can send the second information to the digital assistant server so that the digital assistant server performs natural language processing on the second information.

[0164] Among them, the information generated after natural language processing of the second information can be generated based on the digital assistant calling the language model, that is, the digital assistant server can call the language model, perform natural language processing on the second information, and obtain the information generated after natural language processing of the second information.

[0165] Next, the digital assistant server can send the information generated after natural language processing of the second information to the information processing server. The information processing server receives the information generated after natural language processing of the second information by the digital assistant server, thereby completing the step of the information processing server calling the digital assistant server.

[0166] S404: Determine reply information for the first information based on information generated after the digital assistant server performs natural language processing on the second information, and send the reply information for the first information to the client.

[0167] Since the digital assistant performs natural language processing on the second information that does not include key information, the information generated by the digital assistant server also does not include key information. However, the first information input by the user on the client includes key information, and considering that the reply information has the same content as the first information, the information processing server can restore the content of the information generated by the digital assistant server and determine the reply information for the first information.

[0168] In specific implementation, the information processing server can identify the same information existing in the second information in the information generated by the digital assistant server after performing natural language processing on the second information, and then replace the same information in the information generated by the digital assistant server after performing natural language processing on the second information with the key information in the first information, and determine the reply information of the first information based on the replaced information generated by the digital assistant server after performing natural language processing on the second information.

[0169] In other words, the information processing server first determines the same information that needs to be restored, and then replaces the key information in the first information for the same information that needs to be restored, to achieve content restoration, and determines the information after content restoration as the reply information of the first information, so that the reply information is consistent with the content of the first information.

[0170] For example, when the key information in the first information is the user name "Zhang XX", during the information processing process, "Zhang XX" is replaced with "user Xiao Zhang". After the digital assistant server performs natural language processing on the second information, the generated information may include "user Xiao Zhang". The information processing server can store the correspondence between the first information and the second information, and restore the "user Xiao Zhang" included in the information generated by the digital assistant server to "Zhang XX".

[0171] After completing the content restoration, the information processing server may send the reply information of the first information to the client, so that the client presents the reply information of the first information, completing a round of human-computer dialogue.

[0172] In this method, the information processing server can process the first information sent by the client, generate the second information that does not include the key information, and then call the digital assistant server to process the second information, and finally determine the reply information of the first information. In this way, through the information processing process, the key information is prevented from being transmitted to the digital assistant server, and the information processing requirements are met.

[0173] The above combined with Figure 1 to Figure 4 The information processing method provided in the embodiment of the present application is introduced in detail. The device and equipment provided in the embodiment of the present application will be introduced in conjunction with the accompanying drawings.

[0174] See also Figure 5 The structural diagram of the information processing device shown in FIG. 5 includes:

[0175] A determination module 501 is used to determine a processing judgment result of the first information in response to a sending request of the first information; wherein the first information represents natural language content, the sending request is used to trigger interaction with the digital assistant server, and the processing judgment result indicates whether to process the first information;

[0176] The communication module 502 is used to process the first information in response to the processing judgment result indicating that the first information is processed, and send the first information to an information processing server; wherein the information processing server is used to process the first information into second information, the first information includes key information, and the second information does not include the key information;

[0177] The communication module 502 is also used to receive reply information of the first information returned by the information processing server, and the reply information of the first information is determined based on the information generated after the digital assistant server performs natural language processing on the second information.

[0178] In some possible implementations, the determining module 501 is specifically configured to:

[0179] A processing and judgment result of the first information is determined according to a key information identification result of the first information or a source scenario of the first information; wherein the key information identification result indicates whether the first information includes key information.

[0180] In some possible implementations, the determining module 501 is specifically configured to:

[0181] In response to the first information including key information, or the source scenario of the first information requires information processing, it is determined that the processing judgment result of the first information indicates that the first information is to be processed.

[0182] In some possible implementations, the communication module 502 is further configured to:

[0183] In response to the processing determination result indicating that the first information is not to be processed, sending the first information to the digital assistant server;

[0184] Receive reply information for the first information returned by the digital assistant server.

[0185] The information processing device 50 according to the embodiment of the present application may correspond to executing the method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the information processing device 50 are respectively to implement Figure 2 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.

[0186] See also Figure 6 The structural diagram of the information processing device shown in FIG. 60 includes:

[0187] Communication module 601, used to receive first information sent by a client, where the first information represents natural language content;

[0188] A processing module 602 is used to process the first information into second information, where the second information does not include key information in the first information;

[0189] The communication module 601 is further used to send the second information to the digital assistant server, and receive information generated by the digital assistant server after performing natural language processing on the second information; wherein the information generated after performing natural language processing on the second information is generated based on the language model called by the digital assistant server;

[0190] The communication module 601 is also used to determine reply information of the first information based on information generated after the digital assistant server performs natural language processing on the second information, and send the reply information of the first information to the client.

[0191] In some possible implementations, the processing module 602 is specifically configured to:

[0192] Identifying key information in the first information and a location of the key information;

[0193] The key information is processed according to the position of the key information to generate second information that does not include the key information.

[0194] In some possible implementations, the processing module 602 is specifically configured to:

[0195] determining, according to the task type represented by the first information, an information processing strategy for the first information;

[0196] According to the information processing strategy, the first information is processed into second information.

[0197] In some possible implementations, the processing module 602 is specifically configured to:

[0198] Sending the first information to a task type recognition model, and receiving the task type returned by the task type recognition model; wherein the task type recognition model is used to classify natural language processing tasks;

[0199] An information processing strategy for the first information is determined according to the task type.

[0200] In some possible implementations, the information processing strategy includes at least one of the following:

[0201] A strategy for replacing the key information with set characters;

[0202] strategies to hide said critical information;

[0203] Generate a replacement token based on the key information, and replace the key information with a strategy for the replacement token;

[0204] A policy for replacing the key information with setting information matching the key information type.

[0205] In some possible implementations, the communication module 601 is specifically used to:

[0206] Identify information that is identical to the second information in information generated by the digital assistant server after performing natural language processing on the second information;

[0207] Replacing the same information in the information generated by the digital assistant server after performing natural language processing on the second information with the key information in the first information;

[0208] Determine reply information for the first information based on information generated by the replaced digital assistant server after natural language processing of the second information.

[0209] The information processing device 60 according to the embodiment of the present application may correspond to executing the method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the information processing device 60 are respectively to implement Figure 4 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.

[0210] The present application also provides an electronic device. The electronic device is specifically used to implement Figure 5 The function of the information processing device 50 in the embodiment shown is to realize the following Figure 6 The functions of the information processing device 60 in the illustrated embodiment.

[0211] Figure 7 A schematic diagram of the structure of an electronic device 700 is provided. Figure 7 As shown, the electronic device 700 includes a bus 701, a processor 702, a communication interface 703 and a memory 704. The processor 702, the memory 704 and the communication interface 703 communicate with each other via the bus 701.

[0212] The bus 701 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0213] The processor 702 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0214] The communication interface 703 is used for communicating with the outside. For example, the communication interface 703 can be used for communicating with a terminal.

[0215] The memory 704 may include a volatile memory, such as a random access memory (RAM). The memory 704 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0216] The memory 704 stores executable codes, and the processor 702 executes the executable codes to perform the aforementioned information processing method.

[0217] Specifically, in implementing Figure 5 or Figure 6 In the case of the embodiment shown, and Figure 5 or Figure 6 When each module or unit of the information processing device 50 or the information processing device 60 described in the embodiment is implemented by software, the execution Figure 5 or Figure 6 The software or program code required for the functions of each module / unit in the system may be partially or completely stored in the memory 704. The processor 702 executes the program code corresponding to each unit stored in the memory 704 to perform the aforementioned information processing method.

[0218] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned information processing method applied to the information processing device 50, or instruct the computing device to execute the above-mentioned information processing method applied to the information processing device 60.

[0219] The embodiment of the present application further provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part.

[0220] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0221] When the computer program product is executed by a computer, the computer executes any of the aforementioned information processing methods. The computer program product may be a software installation package, and when any of the aforementioned information processing methods is needed, the computer program product may be downloaded and executed on a computer.

[0222] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to each embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0223] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the unit / module does not, in some cases, constitute a limitation on the unit itself.

[0224] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0225] In the context of the present application embodiment, machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0226] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0227] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0228] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0229] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0230] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method, characterized in that: Applied to a client, the method comprises: In response to a request to send first information, determining a processing judgment result of the first information; wherein the first information represents natural language content, the sending request is used to trigger interaction with a digital assistant server, and the processing judgment result indicates whether to process the first information; In response to the processing judgment result indicating that the first information is to be processed, the first information is sent to an information processing server; wherein the information processing server is used to process the first information into second information, the first information includes key information, and the second information does not include the key information; Receive reply information for the first information returned by the information processing server, where the reply information for the first information is determined based on information generated after the digital assistant server performs natural language processing on the second information.

2. The method according to claim 1, characterized in that The determining a result of processing and judging the first information includes: A processing and judgment result of the first information is determined according to a key information identification result of the first information or a source scenario of the first information; wherein the key information identification result indicates whether the first information includes key information.

3. The method according to claim 2, characterized in that The determining, according to the key information identification result of the first information or the source scenario of the first information, the processing and judgment result of the first information includes: In response to the first information including key information, or the source scenario of the first information requires information processing, it is determined that the processing judgment result of the first information indicates that the first information is to be processed.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: In response to the processing determination result indicating that the first information is not to be processed, sending the first information to the digital assistant server; Receive reply information for the first information returned by the digital assistant server.

5. An information processing method, characterized in that: Applied to an information processing server, the method comprises: Receiving first information sent by a client, where the first information represents natural language content; Processing the first information into second information, where the second information does not include key information in the first information; Sending the second information to the digital assistant server, and receiving information generated by the digital assistant server after performing natural language processing on the second information; wherein the information generated after performing natural language processing on the second information is generated based on the language model called by the digital assistant server; Determine reply information for the first information based on information generated after the digital assistant server performs natural language processing on the second information, and send the reply information for the first information to the client.

6. The method according to claim 5, characterized in that The processing of the first information into second information includes: Identifying key information in the first information and a location of the key information; The key information is processed according to the position of the key information to generate second information that does not include the key information.

7. The method according to claim 5, characterized in that The processing of the first information into second information includes: determining, according to the task type represented by the first information, an information processing strategy for the first information; According to the information processing strategy, the first information is processed into second information.

8. The method according to claim 7, characterized in that The determining, according to the task type represented by the first information, an information processing strategy for the first information includes: Sending the first information to a task type recognition model, and receiving the task type returned by the task type recognition model; wherein the task type recognition model is used to classify natural language processing tasks; An information processing strategy for the first information is determined according to the task type.

9. The method according to claim 7, characterized in that: The information processing strategy includes at least one of the following: A strategy for replacing the key information with set characters; strategies to hide said critical information; Generate a replacement token based on the key information, and replace the key information with a strategy for the replacement token; A policy for replacing the key information with setting information matching the key information type.

10. The method according to any one of claims 5 to 9, characterized in that: The determining, according to the information generated by the digital assistant server after performing natural language processing on the second information, reply information of the first information includes: Identify information that is identical to the second information in information generated by the digital assistant server after performing natural language processing on the second information; Replacing the same information in the information generated by the digital assistant server after performing natural language processing on the second information with the key information in the first information; Determine reply information for the first information based on information generated by the replaced digital assistant server after natural language processing of the second information.

11. An information processing device, characterized in that: Deployed on the client, the device includes: a determination module, configured to determine, in response to a request for sending first information, a processing judgment result of the first information; wherein the first information represents natural language content, the sending request is used to trigger interaction with a digital assistant server, and the processing judgment result indicates whether to process the first information; a communication module, configured to process the first information in response to the processing judgment result indicating that the first information is processed, and send the first information to an information processing server; wherein the information processing server is configured to process the first information into second information, the first information includes key information, and the second information does not include the key information; The communication module is also used to receive reply information of the first information returned by the information processing server, and the reply information of the first information is determined based on the information generated after the digital assistant server performs natural language processing on the second information.

12. An information processing device, characterized in that: Deployed on the information processing server, the device includes: A communication module, configured to receive first information sent by a client, wherein the first information represents natural language content; a processing module, configured to process the first information into second information, wherein the second information does not include key information in the first information; The communication module is further used to send the second information to the digital assistant server, and receive information generated by the digital assistant server after performing natural language processing on the second information; wherein the information generated after performing natural language processing on the second information is generated based on the language model called by the digital assistant server; The communication module is also used to determine reply information of the first information based on information generated after the digital assistant server performs natural language processing on the second information, and send the reply information of the first information to the client.

13. An electronic device, characterized in that: The electronic device comprises a processor and a memory; The processor is used to execute the instructions stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 4, or executes the method according to any one of claims 5 to 10.

14. A computer-readable storage medium, characterized in that: The method comprises instructions, wherein the instructions instruct an electronic device to execute the method according to any one of claims 1 to 4, or instruct an electronic device to execute the method according to any one of claims 5 to 10.

15. A computer program product, characterized in that The computer program product comprises computer-readable instructions, and the computer-readable instructions are used to implement the method according to any one of claims 1 to 4, or to implement the method according to any one of claims 5 to 10.

Images