Semantic communication for low bit rate applications
By detecting the quality of wireless network connections in wireless devices and generating reduced-size messages using predetermined phrases, natural language processing or compression techniques, the problem of low transmission success rate at limited bandwidth and high block error rates is solved, and more efficient Network utilization and emergency message transmission.
Patent Information
- Application Number
- CN202411305559.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-01-31
- Filing Date
- 2022-06-29
- Publication Date
- 2024-11-01
AI Technical Summary
In the case of limited network bandwidth or high block error rate, the prior art is difficult to effectively improve the transmission success rate and reduce delays when transmitting messages, and it is difficult for the equipment to send emergency messages when it is poor wireless network connection.
When a message request is received through a wireless device, the wireless network connection quality is detected. If the threshold is not met, a predetermined phrase, natural language processing model or compression engine is used to generate a reduced size message, reducing the amount of data to improve the transmission success rate. Specific methods Including using predetermined codes, phrase probability prediction, message overview, or encoding, to generate a smaller bit string than the original message.
More efficient network bandwidth usage, reduced block error rate, reduced power consumption, reduced delivery delay and improved transmission success rate, ensuring that emergency messages can be sent in case of poor connections.
Smart Images

Figure CN118890656A_ABST
Abstract
Description
[0001] This application is a divisional application of the Chinese invention patent application with the application date of June 29, 2022, the national application number 202210761360.8, and the invention name “Semantic Communication for Low Bit Rate Applications”.
[0002] CROSS-REFERENCE TO RELATED APPLICATIONS
[0003] This application claims the benefit of U.S. Provisional Application No. 63 / 237,982, filed on August 27, 2021, entitled “Semantic Communication For Low Bit Rate Applications,” which is incorporated herein by reference in its entirety. Technical Field
[0004] The present specification relates to systems and techniques for sending messages across a network when there is limited network bandwidth, high block error rates, or both. Background Art
[0005] Electronic devices can communicate with each other via one or more wireless networks. For example, a device can communicate with another device across a cellular network. The communication may include voice data, message data, or other appropriate types of data. Summary of the invention
[0006] When the quality of the connection to the wireless network does not meet the connection quality threshold, the wireless device may determine whether to send a reduced size message across the wireless network. For example, the wireless device may determine that the message meets the priority threshold (e.g., determines that the message is an emergency message) and determine to reduce the size of the message when the quality of the connection does not meet the connection quality threshold. The wireless device may reduce the message size using predetermined codes for one or more predetermined phrases, context-aware phrase likelihood predictions, context summarization, message encoding, or a combination of two or more of these. By sending the reduced size message, the wireless device may increase the likelihood of successfully sending the message to the target device across the wireless network.
[0007] In general, one aspect of the subject matter described in this specification can be embodied in methods, which include: an act of receiving, by a wireless device, a request to send a message including one or more phrases over a wireless network; determining that a connection quality of the wireless network does not meet a connection quality threshold; in response to determining that the connection quality threshold is not met, generating a reduced size message based at least in part on the one or more phrases; and sending the reduced size message by the wireless device and over the wireless network. Other embodiments of this aspect include corresponding computer systems, apparatus, computer program products, and computer programs recorded on one or more computer storage devices, each configured to perform the acts of the method. A system of one or more computers can be configured to perform the acts by having software, firmware, hardware, or a combination thereof installed on the system that causes the system to perform specific operations or actions in operation. One or more computer programs can be configured to perform the acts by including instructions that, when executed by a data processing device, cause the device to perform specific operations or actions.
[0008] The foregoing embodiments and other embodiments may each optionally include one or more of the following features, alone or in combination: In some implementations, determining that a connection quality threshold is not met may include determining that a network strength indicator associated with the wireless network does not meet a network strength indicator threshold.
[0009] In some implementations, the method may include determining a connection quality in response to determining, based at least in part on the message, that the message is to be considered associated with an emergency services system. The determination to consider the message to be associated with the emergency services system may be based at least in part on a destination address of the message. The determination to consider the message to be associated with the emergency services system may be based at least in part on an indication that the wireless device attempted to perform an emergency call within a threshold time period of receiving a request to send a message over a wireless network.
[0010] In some implementations, the method may include: in response to receiving a request to send a message, attempting to send a message over a wireless network; and determining that the attempt to send the message over the wireless network was unsuccessful. Determining that a connection quality of the wireless network does not satisfy a connection quality threshold may be responsive to determining that the attempt to send the message over the wireless network was unsuccessful. Generating a reduced-size message may include: detecting a predefined phrase from among the one or more phrases; and generating, in a body of the reduced-size message, a reduced-size message including a bit string mapped to the predefined phrase, the bit string having fewer bits than the predefined phrase.
[0011] In some implementations, generating a reduced-size message may include: using, at least in part, a natural language processing model to predict a likelihood of a next phrase following a phrase in one or more phrases; determining that the likelihood of the next phrase following the phrase satisfies a threshold likelihood; determining that the next phrase occurs after the phrase in the one or more phrases; and in response to determining that the next phrase occurs after the phrase in the one or more phrases and satisfies the threshold likelihood, encoding a representation of the next phrase in a body of the reduced-size message, the representation having fewer bits than the next phrase. The method may include: determining the threshold likelihood based, at least in part, on the number of characters included in the one or more phrases. The natural language processing model may receive as input data representing a phrase. The natural language processing model may be trained to predict the likelihood that a phrase will occur after an input phrase.
[0012] In some implementations, generating a reduced-size message may include: using, at least in part, a natural language processing model to predict a likelihood of a next phrase that follows a phrase in one or more phrases; determining that the likelihood of the next phrase following the phrase does not satisfy a threshold likelihood; determining that the next phrase occurs after the phrase in the one or more phrases; and in response to determining that the likelihood of the next phrase occurring after the phrase in the one or more phrases and not satisfying the threshold likelihood, encoding the phrase in a body of the reduced-size message. In some examples, when the natural language processing model determines the likelihood of multiple phrases from the one or more phrases, the natural language processing model may determine two likelihoods for the same phrase when each of the likelihoods is based, at least in part, on a different context of the phrase in the one or more phrases. The different contexts may be different antecedent phrases in the one or more phrases, different following phrases in the one or more phrases, or both.
[0013] In some implementations, generating a reduced-size message may include: using a compression engine that generates a human-readable summary based on human-readable input, generating a human-readable summary corresponding to one or more phrases, the human-readable summary having fewer bits than the one or more phrases; and including the human-readable summary in a body of the reduced-size message. The method may include: after sending the reduced-size message, determining that an updated connection quality of the wireless network satisfies a connection quality threshold; and sending, by the wireless device, a second message over the wireless network based on the message, the second message having more bits than the reduced-size message. The message and the second message may include the same body. The second message may include the reduced-size message excluding the human-readable summary.
[0014] In some implementations, generating the reduced size message may include: providing one or more phrases as input to an encoder trained to generate a compressed bitstream using at least in part the model to cause the encoder to generate a compressed bitstream having fewer bits than the one or more phrases; and generating the reduced size message based at least in part on the model including the compressed bitstream, the compressed bitstream being decodable to produce an uncompressed version of the one or more phrases. The request to send the message may request to send the message via a cellular network. The request to send the message may request to send the message via a satellite network.
[0015] The subject matter described in this specification can be implemented in various embodiments and can produce one or more of the following advantages. The systems and methods described in this specification can reduce the size of messages, thereby creating messages of reduced size for more efficient network bandwidth usage, reduced block error rate, reduced delivery delay, increased successful transmission rate, or a combination of two or more of these. For example, creating messages of reduced size can reduce delivery delay, increase successful delivery rate, or both, while maintaining the same block error rate as other systems. In some examples, using longer messages (e.g., messages that are not reduced in size) may result in more retransmissions than using messages of reduced size, which may cause the device sending the longer message to be more likely to reach a maximum retransmission threshold or a delay threshold, and therefore have a higher delivery failure rate. Therefore, using messages of reduced size can increase the likelihood that a device does not reach a maximum retransmission threshold, a delay threshold, or both.
[0016] In some implementations, reducing the size of a message can enable a wireless device to send a reduced size message across a wireless network when the wireless device would otherwise be unable to send a non-reduced size message across the wireless network. This can enable communication of urgent messages when such communication might otherwise be unavailable. In some implementations, generation, transmission, or both of reduced size messages can enable a wireless device to send more important messages faster, send more important messages with a higher probability of being transmitted, or both, compared to less important messages.
[0017] In some implementations, a device implementing the systems and methods described in this specification may have reduced power compared to other devices. For example, a device with a poor wireless network connection (e.g., difficult radio conditions) may typically have a high transmit ("tx") power usage that may be proportional to the size of the message the device is attempting to send. By reducing the size of the message, the device may reduce the power required to send the message compared to the power required without the reduced size message. In some implementations, the systems and methods described in this specification may reduce the bandwidth occupancy of the network, which may reduce network congestion, improve message delivery success rates, improve network latency, or a combination of two or more of these. When a network has reduced bandwidth occupancy, the network may route traffic more efficiently, serve more devices simultaneously, or both.
[0018] Details of one or more specific implementations of the subject matter described in this specification are set forth in the following drawings and the specification. Other features, aspects, and advantages of the subject matter will become apparent from the specification, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 An exemplary environment is depicted in which a wireless device connects to a base station using a wireless connection.
[0020] Figure 2 Some examples of predetermined phrases with corresponding codes are depicted.
[0021] Figure 3 An example of a user interface with phrase likelihood predictions is depicted.
[0022] Figure 4 is a flow chart of a process for determining whether to send a reduced size message.
[0023] Figure 5 is a block diagram of a computing device.
[0024] Like reference numbers and designations in the various drawings indicate like elements. DETAILED DESCRIPTION
[0025] Sometimes wireless network connections may be poor. In some examples, poor connections may be caused by wireless network bandwidth being scarce, expensive, or both. Poor connections may be caused by suboptimal wireless radio conditions. For example, in certain geographic locations, such as mountains or valleys or areas with tree cover, wireless (e.g., terrestrial and / or non-terrestrial) bandwidth may be scarce. Sometimes, a wireless network may have a high block error rate ("BLER"), which may cause a wireless device to attempt to retransmit large messages more frequently than if the wireless network had a lower BLER.
[0026] To increase the likelihood of sending a message across a poor wireless network connection, the wireless device may reduce the size of the message so that less data needs to be sent across the poor wireless network connection. The wireless device may reduce the message size using predetermined codes for predetermined phrases, codes for phrases that meet a threshold likelihood of being the next typed phrase (e.g., phrase likelihood prediction), message summarization, message encoding, or a combination of two or more of these. Examples of these processes are described in more detail below.
[0027] When the wireless device sends the message summary, the wireless device may later determine whether the wireless connection has improved. If so, the wireless device may potentially send the original message in a reduced size, such as using one or more of the other methods described in this specification, instead of the message summary. The reduced size message includes fewer bits or bytes than the original message.
[0028] In some implementations, the wireless device may use multiple different connection quality thresholds. Depending on the connection quality threshold that is not met, the wireless device may use different procedures for reducing the message size. For example, when the connection quality does not meet (e.g., is less than or equal to, or either) a minimum connection quality threshold, the wireless device may use at least a message summarization procedure to reduce the message size. When the connection quality meets (e.g., is greater than or equal to, or either) a minimum connection quality threshold but does not meet another connection quality threshold, the wireless device may use a predetermined code of at least a predetermined phrase to generate a message of reduced size.
[0029] Figure 1 An exemplary environment 100 is depicted in which a wireless device 102 is connected to base stations 106a-106b using a wireless connection 104. The wireless device 102 may analyze the connection quality of the wireless connection 104 to determine whether to send a reduced size message via the wireless connection 104.
[0030] For example, the wireless device 102 may include a messaging application 108. The messaging application 108 may be any suitable type of messaging application, such as a text messaging application, an instant messaging application, or another type of real-time messaging application.
[0031] The wireless device 102 may use the wireless connection 104 to communicate with other devices, such as a target device 128, using the messaging application 108. For example, the wireless device 102 may use the messaging application 108 to send a message to a target device 128 operated by a friend, family member, or co-worker of the user. In some examples, the wireless device 102 may use the messaging application 108 to communicate with an emergency services system including the target device 128.
[0032] The wireless device 102 includes an input device 110 configured to enable a user to enter messages into the messaging application 108. To name a few examples, the input device 110 may include a keyboard, a mouse, a tactile input, a microphone, or a combination of these. The keyboard may be a touch screen keyboard, a hardware keyboard, or any other suitable type of keyboard.
[0033] The wireless device 102 may include a display 112 on which content is presented. For example, the wireless device 102 may present a user interface for the messaging application 108 on the display 112. The display 112 may be any suitable type of display, such as a touch screen display.
[0034] In some examples, the wireless device 102 may include a speaker 114. Instead of or in addition to the display 112, the wireless device 102 may include a speaker 114. The wireless device 102 may present audible content to a user using the speaker 114. For example, the wireless device 102 may receive a message from the messaging application 108 and present the content of the message using the speaker 114, the display 112, or both.
[0035] The wireless device 102 includes a wireless radio 116. The wireless radio 116 is configured to enable the wireless device 102 to communicate using the wireless connection 104. Some examples of the wireless radio 116 may include a radio that enables the wireless device 102 to connect to a non-terrestrial (e.g., satellite and / or high altitude platform (“HAP”)) base station 106 a, a cellular radio that enables the wireless device 102 to connect to a cellular base station 106 b, or both.
[0036] The wireless device 102 includes a compression engine 118. The compression engine 118 or another component in the wireless device 102 can determine whether to send a reduced size message. For example, the compression engine 118 can receive connection quality data from a component in the wireless device 102 (e.g., the wireless radio component 116). The connection quality data can be a network strength indicator for the wireless connection 104, such as a received signal strength indicator ("RSSI").
[0037] The wireless device 102 (eg, the compression engine 118) can compare the connection quality data to a connection quality threshold. Based on the comparison, the wireless device 102 can determine whether to reduce the size of the message for the messaging application 108.
[0038] For example, wireless device 102 may receive data from messaging application 108 identifying message 124 that messaging application 108 is attempting to send. The data may indicate an intended destination device for message 124, such as destination device 128. For example, the data may include a destination address for message 124. The destination address may be any suitable type of address, such as a phone number, an email address, an IP address, or another suitable address. When message 124 is “I have an emergency,” the destination address may identify an emergency services system.
[0039] The wireless device 102 may receive, for example, from the wireless radio 116, a connection quality of the wireless connection 104 across which the message 124 may be sent. The wireless device 102 may compare the connection quality of the wireless connection 104 to a connection quality threshold. For example, when the connection quality is a numerical value, the wireless device 102 may compare the numerical value of the connection quality to another numerical value of the connection quality threshold.
[0040] When the wireless device 102 determines that the connection quality meets (e.g., is greater than or equal to, or either) the connection quality threshold, the wireless device 102 may send the message 124. For example, the wireless device 102 may use the wireless radio 116 to send the message 124 via the wireless connection 104. The sent message 124 may be in an uncompressed format, or in another normal format for the messaging application 108, depending on how messages of the messaging application 108 are sent across the network.
[0041] When the wireless device 102 determines that the connection quality does not meet (e.g., is less than or equal to, or either) the connection quality threshold, the wireless device 102 may determine to use the compression engine 118 to generate the reduced size message 126. The compression engine 118 may use the connection quality threshold that is not met, the degree to which the connection quality does not meet the connection quality threshold, the importance of the message 124, the length of the message 124, or a combination of these to determine the type of compression to use. For example, when the connection quality is closer to the connection quality threshold, the compression engine 118 may select a faster compression process, a process that does not compress the message as much, or a process that does both, than when the connection quality is further away from the connection quality threshold. When the connection quality is further away from the connection quality threshold, the compression engine 118 may select a slower process, a process that compresses more, or both, than when the connection quality is closer to the connection quality threshold.
[0042] exist Figure 1In the example shown, the compression engine 118 uses the predetermined codes to compress the message 124. For example, the compression engine 118 may include a database that maps predetermined phrases with predetermined codes. When the compression engine 118 receives the message 124 to be compressed, the compression engine 118 may analyze the text of the message 124 to determine whether the text of the message 124 includes any predetermined phrases, and replace any occurrences of the predetermined phrases with corresponding predetermined codes from the database.
[0043] Figure 2 Some examples of predetermined phrases with corresponding codes are depicted. Figure 2 , the wireless device 102 presents a user interface 200 through which the wireless device 102 receives an input 202 of the message 124 “I have an emergency” during time T0 .
[0044] During time T1, compression engine 118 may determine whether input 202 includes any predetermined phrases. For example, when compression engine 118 determines that input 202 includes predetermined phrase 204a (such as "Emergency"), compression engine 118 may replace predetermined phrase 204a with predetermined code 206a corresponding to predetermined phrase 204a in the mapping, in the body of message 124 or input 202, for example by accessing the mapping using predetermined phrase 204a as a key. In this example, compression engine 118 replaces predetermined phrase 204a with predetermined code 206a " <sop> 0 <eop>” replaces the predetermined phrase 204a “Emergency” to generate a reduced size message 126. In the predetermined code, “sop” means “beginning of phrase” and “eop” means “end of phrase”. Other identifiers may be used to indicate the beginning and end of the predetermined code.
[0045] By sending the reservation code" <sop> 0 <eop>” instead of a predetermined phrase, such as the word “emergency,” the compression engine 118 can reduce the size of the message 124 from 18 characters to 12 characters in the reduced-size message 126. By reducing the amount of data to be transmitted, the wireless device 102 can increase the likelihood that the reduced-size message 126 will be successfully received by the target device 128 compared to the message 124.
[0046] Some other predetermined phrases 204b-204c may include "Help is coming soon" 204b and "Don't worry" 204c. The predetermined phrase may include a single word. The predetermined phrase may include two or more words. The corresponding predetermined codes 206b-206c of these predetermined phrases 204b-204c may include "3" and "4". Although these predetermined phrases 204b-204c may be received by the wireless device 102 instead of as Figure 2 1 and 2. The wireless device 102 is shown as sending the predetermined phrases 204b-204c, but these predetermined phrases 204b-204c are shown as examples of codes. In addition, the wireless device 102 can include these predetermined phrases 204b-204c in the mapping so that when the wireless device 102 receives the corresponding predetermined codes 206b-206c from the target device 128 in a response, the wireless device 102 can decode these predetermined codes 206b-206c.
[0047] In some examples, the wireless device 102 (e.g., the compression engine 118) may include the predetermined codes 206a-206c in the body of the reduced-size message 126, e.g., in the body of the message in the same position relative to other phrases in the body as the corresponding predetermined phrase 204a-204c that the predetermined codes 206a-206c are replacing. The predetermined codes 206a-206c (e.g., a bit string representing the predetermined codes) may have fewer characters, fewer bits, fewer bytes, or a combination of these than the corresponding predetermined phrases.
[0048] return Figure 1 , the target device 128 may receive the reduced size message 126, for example, using the network connection 132. The target device 128 may provide the reduced size message 126 to the decompression engine 130 that recreates the message 124. For example, the decompression engine 130 may access a copy of its own mapping that uses the code as a key to associate a predetermined phrase with a predetermined code. The decompression engine 130 may then generate the message 124 or another message that includes "I have an emergency" in the body of the message 124. The target device 128 may then perform an action using the message 124, such as, for example, presenting the message 124 on a display or using a speaker, or performing an automated action. The target device 128 may present the message on a display, for example, to an emergency service person. The automated action may include sending an instruction to dispatch an emergency vehicle to a physical location near the physical location of the wireless device 102.
[0049] In some implementations, the predetermined phrase may be a common phrase, or a common phrase in a particular context, such as an emergency situation. For example, the system may analyze a plurality of messages, such as the messaging application 108 or a plurality of messaging applications, to determine a phrase included in the message and the frequency with which the phrase appears in the message. When the frequency meets a threshold frequency, such as the number of occurrences or the percentage of messages in which the phrase appears, the system may add the phrase and the corresponding code to a map. The compression engine 118 may then receive a map from the system that identifies the common phrase and the corresponding code.
[0050] When the compression engine 118 generates the reduced size message 126, the compression engine 118 can access the mapping to determine the corresponding code and include the code instead of the corresponding common phrase in the body of the reduced size message 126. The target device 128 can then use the same mapping, for example generated by the system, to decompress the message using the decompression engine 130 by using the code as a key to the mapping.
[0051] The compression engine 118 may generate the reduced size message 126 using codes for phrases having at least a threshold likelihood of occurring after the antecedent phrase. Figure 3 An example of a user interface 300 with phrase likelihood predictions is depicted. The user interface 300 is for a messaging application, such as the messaging application 108. The user interface 300 includes a message input field 302. Figure 3 , the message input field 302 includes the text of the antecedent phrase 304 "I am lost in...".
[0052] The wireless device (e.g., compression engine) may use the antecedent phrase 304 to predict the likelihood of the subsequent phrases 306a-306c. Here, the subsequent phrases 306a-306c are "forest", "mall", and "mountain". In some examples, at least some of the subsequent phrases 306a-306c may include two or more words. Some of the subsequent phrases 306a-306c may include only a single word.
[0053] The likelihood 308a-308c of the corresponding subsequent phrases 306a-306c occurring after the antecedent phrase 304 is 45%, 30%, and 10%, respectively. That is, given the antecedent phrase 304 "I am lost in...", there is a 45% likelihood that the subsequent phrase will be "forest", a 30% likelihood that the subsequent phrase will be "mall", and a 10% likelihood that the subsequent phrase will be "mountains". The remaining 15% may correspond to other phrases. The likelihood may be, for example, a normalized likelihood using an amount (e.g., a predetermined amount) of top-ranked phrases.
[0054] The wireless device (e.g., a compression engine) may use a natural language processing ("NLP") model to determine the likelihood. The wireless device may receive an NLP model from a system that trains the NLP model or otherwise stores the NLP model in a memory. In some examples, the system may train the NLP model using a specific context (e.g., an emergency context). For example, rather than training the NLP model to predict the likelihood of a subsequent phrase in any context, the system may train the NLP model to predict the likelihood of a subsequent phrase in an emergency situation. In these examples, the wireless device may use the NLP model to compress the emergency message.
[0055] When generating a message of reduced size, the compression engine may use Huffman encoding or another appropriate type of encoding for subsequent phrases given the possibility of subsequent phrases 306a-306c. For example, for the message "I am lost in the woods", the compression engine may generate a message with the body "I am lost in the woods". 0 For the message "I am lost in the mall", the compression engine may generate a message with the body "I am lost in the mall" that is reduced in size. 1 For the message "I am lost in the mountains", the compression engine can generate a message with the body "I am lost in the mountains". 10 Lost" message with reduced size.
[0056] When the compression engine determines that the subsequent phrase does not have at least a threshold likelihood of following the antecedent phrase, the compression engine may determine to skip replacing the subsequent phrase with encoding. For example, when the message is "I'm lost in a car," the compression engine may determine to skip compressing the message when "car" has a .05% likelihood of following the antecedent phrase "I'm lost in...", may determine to skip compressing the subsequent phrase, may determine to skip compressing the subsequent phrase using phrase likelihood prediction, or a combination of two or more of these. For example, the compression engine may determine to skip compressing the subsequent phrase using phrase likelihood prediction, for example, while also determining to reduce the message size using message summarization, message encoding, or both.
[0057] The compression engine can use a static threshold likelihood or a dynamic threshold likelihood to encode using a phrase. When using a static threshold likelihood, the compression engine can use a predetermined threshold likelihood, for example, input by a developer. Some exemplary static threshold likelihoods include 5% or 10%.
[0058] When using a dynamic threshold probability, the compression engine may use a lower threshold probability when the connection quality is low and a higher threshold probability when the connection quality is high. This may enable the wireless device to compress messages more for poorer connections than for better quality connections.
[0059] In some examples, the compression engine may determine the threshold likelihood based on the type of message. For example, when the wireless device determines that the message has a very high priority (e.g., the emergency situation is more severe), the wireless device may use a higher threshold likelihood to reduce the time to generate the reduced size message than when the message has a lower priority (e.g., and there is no emergency situation or the emergency situation is less severe).
[0060] return Figure 1 , compression engine 118 may generate a message summary for message 124. The message summary may be a human-readable summary generated based on the body of message 124. Compression engine 118 may use the message summary as reduced-size message 126, optionally in conjunction with one or more of the other processes described in this specification to reduce the size of message 124.
[0061] For example, the compression engine 118 may include a machine learning model 120 that receives a phrase as input. The phrase may be the body of the message 124 (e.g., "I have an emergency") or a portion of the body of the message 124. The compression engine 118 may provide the input phrase to the machine learning model 120. Some examples of the machine learning model 120 may include a seq2seq model, a transformer model, a neural network (e.g., a deep neural network), or another suitable model.
[0062] The machine learning model 120 can be trained to generate a summary of the input phrase, e.g., a human-readable summary. For example, the system can train the machine learning model 120 as a text summarization model. The system can provide the machine learning model 120 with text input and expected output to train the machine learning model 120 to summarize the text. In some examples, the system can train the machine learning model 120 to summarize text about emergency situations.
[0063] The compression engine 118 receives a summary of the body of the message 124, e.g., a message summary, from the machine learning model 120. For example, for the message "I have an emergency," the compression engine 118 may receive the summary "Emergency."
[0064] The message summary has fewer bits or bytes than the input from which the summary was generated. For example, for the input phrase "I have an emergency," the machine learning model 120 may generate a message summary "Emergency" that has fewer bits and bytes than the input phrase.
[0065] When target device 128 receives the message summary, target device 128 may not decompress the message summary using decompression engine 130. For example, because the message summary contains human-readable text, target device 128 may present the body of the message summary (e.g., "Emergency") on a display, and there is no need to use decompression engine 130 to decompress the message summary.
[0066] In some examples, target device 128 decompresses the message summary using decompression engine 130. For example, when one or more other processes are used to reduce the size of the message summary, decompression engine 130 can use the corresponding process to determine the human-readable message summary.
[0067] The compression engine 118 may perform one or more other processes on the received message summary. For example, the compression engine 118 may use predetermined phrases, phrase likelihood predictions, message encoding, or a combination of two or more of these on the message summary.
[0068] When the wireless device 102 determines that the connection quality of the wireless connection 104 meets the connection quality threshold, the wireless device 102 can send a non-summarized message. For example, the wireless device 102 can send the message 124 or the reduced size message 126 after sending the message summary.
[0069] Specifically, the wireless device 102 may determine that the connection quality does not meet the connection quality threshold. Therefore, the compression engine 118 may generate a message summary. The wireless device 102 may send the message summary to the target device 128 via the wireless connection 104.
[0070] The target device 128 may receive the message summary. For example, when the size of the message summary is reduced using another suitable process, the target device 128 may provide the message summary to the decompression engine 130. The target device 128 may then perform an action (e.g., an automated action) based on the message summary, present the message summary in a user interface, or both.
[0071] When the wireless device 102 determines that the connection quality meets the connection quality threshold, the wireless device 102 may determine to send a non-summarized message to the target device 128. For example, the wireless device 102 may determine to send the message 124, the reduced size message 126, or both to the target device 128. Here, the wireless device 102 will use a process other than message summary generation to generate the reduced size message 126. In some examples, when the wireless device 102 has multiple connection quality thresholds, the wireless device 102 may send both the message 124 and the reduced size message 126.
[0072] In some implementations, the wireless device 102 may have multiple connection quality thresholds. For example, the wireless device 102 may have two or more connection quality thresholds. The two or more connection quality thresholds may include a highest connection quality threshold and a lowest connection quality threshold. The wireless device 102 may compare the connection quality of the wireless connection 104 used to send the message 124 with one or more of the two or more connection quality thresholds. This may include the wireless device 102 comparing the connection quality with the highest connection quality threshold. If the connection quality meets (e.g., is greater than or equal to or either) the highest connection quality threshold, the wireless device 102 may determine to send the message 124, e.g., a non-reduced size message. The non-reduced size message may be a message generated by the messaging application 108 by default, a message that is not reduced in size by the process described in this specification, or both. The message generated by the messaging application 108 by default may use one or more compression methods specific to the messaging application 108, which are always performed on the messages of the messaging application and are separate from the compression methods described with respect to the compression engine 118.
[0073] If the connection quality does not meet (e.g., is less than or equal to or either) the highest connection quality threshold, the wireless device 102 may determine to send the reduced size message 126. The wireless device 102 may compare the connection quality to other connection quality thresholds other than the highest connection quality threshold among the two or more connection quality thresholds to determine a process by which to generate the reduced size message 126.
[0074] The wireless device 102 may compare the connection quality to a minimum connection quality threshold. If the connection quality meets the minimum connection quality threshold but does not meet the maximum connection quality threshold, the wireless device 102 may determine to generate a reduced size message 126 having a size that is larger than the most compressed reduced size message. For example, the wireless device 102 may determine to generate the reduced size message using predetermined phrases, phrase likelihood predictions, or both, e.g., instead of message summarization, message encoding, or both.
[0075] When the connection quality does not meet the minimum connection quality threshold, the wireless device 102 may determine to generate a reduced size message 126 having a smaller size than if the connection quality met the minimum connection quality threshold. For example, the wireless device may determine to generate a message summary, use message encoding, or both to generate the reduced size message 126.
[0076] In some implementations, the compression engine 118 may use message encoding to generate a reduced size message 126. The compression engine 118 may include an encoder 122 that generates the reduced size message 126. In these implementations, the reduced size message 126 includes the message but does not include the reconstruction information. In contrast, the target device 128 includes a decompression engine 130 having a decoder corresponding to the encoder 122. For example, the decoder is implemented to reconstruct the message 124 from the encoded, reduced size message 126. This may include the decoder recovering the uncompressed original message 124 body, for example, recovering one or more phrases from the body of the message 124.
[0077] When generating the reduced size message 126, the encoder 122 may use any suitable method to compress the message 124. The encoder 122 may use a lossless compression process by which a decoder at the target device 128 can decompress the reduced size message 126 without losing the content (e.g., "I have an emergency") of the message 124. In some examples, the encoder 122 may use a lossy compression process.
[0078] In some examples, the system trains encoder 122 at least in part using the model to generate a compressed bitstream. The system can train a decoder to generate a decompressed bitstream using, for example, the model used to train encoder 122 at least in part. The system can train encoder 122 to produce a compressed bitstream from an input including one or more phrases (e.g., from the body of message 124). The compressed bitstream has fewer bits or bytes than the one or more input phrases.
[0079] In some implementations, the wireless device 102 may determine whether to generate the reduced-size message 126 based on the destination of the message 124. For example, the wireless device 102 may generate the reduced-size message 126 that may have a higher likelihood of successful transmission than the message 124, for example, because of its smaller size, when the destination is: an emergency service system; an emergency contact of the wireless device 102, for example, included in a contact list of the wireless device 102; a frequently called contact of the wireless device 102; a destination that the wireless device 102 knows has a corresponding decompression engine 130; or a destination that is any of a combination of two or more of these. In some examples, the wireless device 102 may determine to generate the reduced-size message 126 when the destination of the message 124 is any contact of the wireless device 102.
[0080] The wireless device 102 may include a personal computer, a mobile communication device, a machine, or another device that can send and receive data via the wireless connection 104. The wireless connection 104 may be part of a network, such as a wide area network ("WAN"), the Internet, a terrestrial network, a non-terrestrial network, or a combination of these, that connects the wireless device 102, one or both of the base stations 106a-106b, and the target device 128. For example, the network may include a network connection 132, such as a wired or wireless network connection 132. The network connection 132 may be part of a local area network ("LAN"), a WAN, the Internet, a terrestrial network, a non-terrestrial network, or a combination of these.
[0081] The wireless device 102 may include several different functional components, including a compression engine 118. The compression engine 118 may include one or more data processing devices. For example, the compression engine 118 may include one or more data processors and instructions that cause the one or more data processors to perform the operations discussed herein.
[0082] The target device 128 may include several different functional components, including a decompression engine 130. The decompression engine 130 may include one or more data processing devices. For example, the decompression engine 130 may include one or more data processors and instructions that cause the one or more data processors to perform the operations discussed herein.
[0083] Figure 4 4 is a flow diagram of a process 400 for determining whether to send a reduced size message. The process 400 may be used by a wireless device 102 from the environment 100, for example.
[0084] The wireless device receives a request to send a message including one or more phrases via a wireless network (402). For example, the wireless device receives the request from an application (e.g., a messaging application or another application) executing on the wireless device. The message can be any suitable type of message, such as an email, a text message, an instant message, or an emergency services message of an emergency services application.
[0085] The wireless device determines whether the connection quality of the wireless network should be analyzed (404). For example, the wireless device may use the destination of the message, the content of the message, or both to determine whether the connection quality of the wireless network should be analyzed. This may enable the wireless device to send more important messages faster, with a higher likelihood of transmission, or both, compared to less important messages. For example, the wireless device may send messages with smaller sizes faster or with a higher likelihood of transmission because the smaller size reduces the number of bits to be transmitted, and these bits may be lost during transmission.
[0086] When the destination indicates an emergency service system, such as an emergency dispatch device, a contact of the wireless device, an emergency contact of the wireless device, or a combination of these, the wireless device may determine that the wireless device should analyze the connection quality. In response to determining that the destination indicates one or more of these specific destinations, the wireless device may determine the connection quality of the wireless network across which the message is to be sent.
[0087] In some examples, the wireless device may determine to analyze the connection quality when the wireless device has attempted to call a particular destination or has called a particular destination, or both, within a predetermined time period. For example, the wireless device may determine to analyze the connection quality when the wireless device determines that it has attempted or may have attempted to perform an emergency call, such as an emergency service system or an emergency contact, or either, within a threshold time period from receiving a request to send a message across a network.
[0088] The threshold time period may be static or dynamic. For example, the threshold time period may be a fixed value determined, for example, by a developer, a user of the wireless device, or another appropriate entity. The wireless device may dynamically determine the threshold time period using, at least in part, the destination of the message or the destination of the emergency call, or both. The wireless device may dynamically determine the threshold time period using, at least in part, the time during the day when the wireless device receives the request. For example, the threshold time period may be longer during the evening and at night than during the day. The threshold time period may be longer when it is dark outside (e.g., when it is raining) than when it is bright outside (e.g., on a sunny day).
[0089] The wireless device may use the content of the message to determine whether to analyze the connection quality. For example, the wireless device may determine whether one or more key phrases are included in the body of the message. If so, the wireless device may determine to analyze the connection quality. If the wireless device determines that the body of the message does not include any key phrases, the wireless device may determine to skip analyzing the connection quality. The key phrases may relate to a specific context, such as an emergency situation.
[0090] The wireless device determines whether a connection quality of the wireless network satisfies a connection quality threshold (406). For example, in response to determining that the connection quality should be analyzed, the wireless device may determine the connection quality. The wireless device may then determine whether the connection quality satisfies the connection quality threshold. In some examples, the wireless device may determine whether the connection quality satisfies one or more of a plurality of different connection quality thresholds.
[0091] The wireless device sends the message via the wireless network (408). For example, in response to determining that the connection quality of the wireless network satisfies a connection quality threshold, the wireless device sends the message via the wireless network. The wireless device may send the message using a default or otherwise normal messaging protocol for the wireless device, the application from which the wireless device received the request, or both. This may include sending the message in a default format for the application, e.g., without using a compression engine to generate a reduced size message, although this may include use of various compression, encryption, or both protocols by the application itself.
[0092] The wireless device generates a reduced size message (410). For example, in response to determining that the connection quality of the wireless network does not meet the connection quality threshold, the wireless device generates the reduced size message. The wireless device may generate the reduced size message as described above. For example, the wireless device may generate the reduced size message using a predetermined code for a predetermined phrase, a code for a phrase that meets a threshold likelihood of being the next typed phrase (e.g., a phrase likelihood prediction), a message summary, a message encoding, or a combination of two or more of these.
[0093] As part of the phrase likelihood prediction process, the wireless device may use, at least in part, a natural language processing model that receives a phrase as an input and is trained to predict the likelihood that a set of predetermined phrases (such as a set of emergency phrases) will occur after the input phrase. This may include providing the phrase to the natural language processing model and receiving the likelihood as an output. Although the specification describes emergency phrases in various examples, other types of predetermined phrases may also be used, such as predetermined driving direction phrases, predetermined auxiliary phrases, or other suitable types of predetermined phrases.
[0094] The wireless device may perform phrase likelihood prediction for each of the one or more phrases (e.g., for all phrases included in the message). For example, the wireless device may determine, for each of the one or more phrases, a likelihood that the emergency phrase is the next phrase after the corresponding phrase. The wireless device may determine whether the likelihood that the emergency phrase is the next phrase after the corresponding phrase satisfies a threshold likelihood. The wireless device may determine that the emergency phrase occurs after the corresponding phrase. In response to determining that the likelihood that the emergency phrase is the next phrase after the corresponding phrase satisfies the threshold likelihood and determining that the emergency phrase occurs after the corresponding phrase, the wireless device may encode a representation of the emergency phrase in the body of the reduced-size message, e.g., " 0 ”. The representation has fewer bits or bytes than the emergency phrase, thereby producing a reduced-size message having fewer bits or bytes than the original message. In response to determining that the emergency phrase does not appear after the corresponding phrase, the wireless device may encode the next phrase after the corresponding phrase in the body of the reduced-size message.
[0095] The wireless device may use a static or dynamic threshold likelihood. For example, the static threshold likelihood may be the same for all messages analyzed, such as a predetermined value set by a developer. The wireless device may determine the dynamic threshold likelihood using, at least in part, the number of characters included in one or more phrases, the quality of the connection to the wireless network, or both.
[0096] In some examples, the next phrase may have a likelihood of occurring after a preceding phrase that does not satisfy a threshold likelihood (e.g., less than, equal to, or either threshold likelihood). In these examples, in response to determining that the likelihood that the urgent phrase is the next phrase after the corresponding phrase does not satisfy the threshold likelihood and determining that the urgent phrase occurs after the corresponding phrase, the wireless device may encode the urgent phrase in the body of the reduced-size message. Specifically, the wireless device may encode the phrase in the reduced-size message with the same number of bits that the phrase would have in the original message.
[0097] In some implementations, the wireless device may determine whether the size reduction process successfully reduced the size of the message. For example, when the wireless device attempts to reduce the size of the message using a predetermined phrase, a phrase likelihood prediction, or both, the wireless device may determine whether the generated message has the same size as the original message or a size within a threshold amount of the original message. When the generated message does not have the same size as the original message or a size within a threshold amount of the original message size, the wireless device may determine that the size reduction process successfully reduced the size of the message. In response, the wireless device may determine to send the size-reduced message to the target device.
[0098] When the generated message has the same size as the original message size or a size within a threshold amount of the original message size, the wireless device may determine that the size reduction process did not successfully reduce the size of the message. In response, the wireless device may select another process that reduces the size of the original message by, for example, using message summarization, message encoding, another process, or a combination of two or more of these.
[0099] The wireless device sends the reduced size message via the wireless network (412). For example, in response to generating the reduced size message, the wireless device may send the reduced size message to a target device identified, for example, by a destination in the original message, the reduced size message, or both.
[0100] The wireless device determines whether the message was successfully sent via the wireless network (414). The message may be the original message (e.g., the request received in step 402) or a reduced size message. The wireless device may use data received from a base station or another device to which the wireless device is connected to determine whether the message was successfully sent. The data may include an acknowledgement indicating that the base station or another device successfully received the message.
[0101] In response to determining that the message was not successfully sent across the network, the wireless device may determine whether the connection quality of the wireless network meets the connection quality threshold, e.g., proceeding to step 406. For example, when the wireless device sends a reduced size message, the wireless device may determine whether it should attempt to resend the reduced size message or the original message based at least in part on the connection quality. In some examples, if the wireless device determines to send the reduced size message again, the wireless device may further reduce the size of the message and send the further reduced size message.
[0102] In some implementations, after performing step 414 and determining that the message was successfully sent via the wireless network, the wireless device can stop performing process 400. For example, the wireless device can wait to receive another message sending request from the messaging application or another application, wait to receive a message from a target device, or perform another appropriate process.
[0103] The wireless device determines whether the reduced size message includes a message summary (416). For example, when the wireless device successfully sends the reduced size message (e.g., in step 414), the wireless device may determine whether the reduced size message includes a message summary. The wireless device may make this determination at least in part using data included in the message, data indicating a process by which the compression engine generated the message (e.g., a flag in a memory), or another suitable process. The wireless device may perform this step at least in part in response to determining that the reduced size message was successfully sent.
[0104] In response to determining that the reduced size message does not include a message summary, the wireless device may stop performing process 400. For example, the wireless device may wait to receive another message send request.
[0105] The wireless device generates a second message that does not include the message summary (418). For example, in response to determining that the reduced-size message includes the message summary, the wireless device may determine to send the second message that does not include the message summary. The second message that does not include the message summary may include the original message, or a reduced-size message generated using a process other than message summary generation (e.g., using predetermined phrase encoding, phrase likelihood prediction, or message encoding).
[0106] In some examples, the wireless device may analyze an updated connection quality of the wireless network after sending the reduced size message including the message summary. After sending the reduced size message, the wireless device may determine that the updated connection quality of the wireless network meets a connection quality threshold, e.g., a connection quality threshold that caused the wireless device to generate the reduced size message using the message summary. In response to determining that the updated connection quality of the wireless network meets the connection quality threshold, the wireless device may send a second message via the wireless network to the target device to which the reduced size message was directed.
[0107] The wireless device may perform any appropriate process in response to determining that the updated connection quality does not meet the connection quality threshold. For example, the wireless device may determine to wait until the connection quality improves. In some examples, the wireless device may determine to send a second message that does not include a message summary.
[0108] The second message without the message summary has more bits than the reduced-size message and is generated at least in part using the message. For example, the second message may have the same body as the original message. The second message may be a reduced-size message that originally did not include the human-readable summary.
[0109] The order of steps in process 400 described above is illustrative only, and determining whether to send a reduced size message is performed in a different order. For example, the wireless device may determine whether the reduced size message includes a message summary before determining whether the message is successfully sent via the wireless network.
[0110] In some implementations, process 400 may include additional steps, fewer steps, or some of these steps may be separated into multiple steps. For example, the wireless device may perform steps 402, 410, and 412 without performing other steps in process 400. The wireless device may perform steps 402, 406, 410, and 412 without performing other steps in process 400. The wireless device may perform steps 406, 410, and 412 without performing other steps in process 400. Other combinations of steps are also contemplated.
[0111] It is understood that the use of personally identifiable information should be subject to privacy policies and practices that are generally recognized to meet or exceed industry or government requirements for maintaining user privacy. Specifically, personally identifiable information data should be managed and processed to minimize the risk of unintentional or unauthorized access or use, and the nature of the authorized use should be clearly stated to users.
[0112] A number of specific implementations have been described. However, it should be understood that various modifications may be made without departing from the spirit and scope of the present disclosure. For example, various forms of the processes shown above may be used, wherein steps have been rearranged, added, or removed.
[0113] The embodiments of the subject matter and functional operations described in this specification may be implemented in digital electronic circuits, in tangibly embodied computer software or firmware, in computer hardware (including the structures disclosed in this specification and their structural equivalents), or in a combination of one or more of them. The embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier, for execution by a data processing device or for controlling the operation of the data processing device. Alternatively or in addition, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information for transmission to a suitable receiver device for execution by a data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
[0114] The term "data processing apparatus" refers to data processing hardware and encompasses all kinds of apparatus, devices and machines for processing data, including, for example, a programmable processor, a computer, or multiple processors or computers. The apparatus may be or also include a dedicated logic circuit (e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit)). In addition to hardware, the apparatus may optionally include code that creates an execution environment for a computer program, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them.
[0115] A computer program (also referred to or described as a program, software, software application, module, software module, script, or code) may be written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program may be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions). A computer program may be deployed to execute on one computer or on multiple computers located at the same site or distributed across multiple sites and interconnected by a communications network.
[0116] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can be performed by special purpose logic circuits (e.g., FPGAs (field programmable gate arrays) or ASICs (application specific integrated circuits)), and the apparatus can also be implemented as special purpose logic circuits.
[0117] Computers suitable for executing computer programs include, for example, general-purpose microprocessors or special-purpose microprocessors or both, or any other kind of central processing unit. Generally speaking, the central processing unit will receive instructions and data from a read-only memory or a random access memory or both. The basic elements of a computer are a central processing unit for performing or executing instructions and one or more memory devices for storing instructions and data. Generally speaking, a computer will also include one or more mass storage devices for storing data (e.g., disks, magneto-optical disks, or optical disks), or be operably coupled to receive data from one or more mass storage devices and / or transfer data to one or more mass storage devices. However, a computer does not need to have such devices. In addition, a computer may be embedded in another device, such as a mobile phone, a smart phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device (e.g., a universal serial bus (USB) flash drive), to name a few.
[0118] Computer-readable media suitable for storing computer program instructions and data include: all forms of non-volatile memory, media and memory devices, including, for example, semiconductor memory devices, such as EPROM, EEPROM and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuits.
[0119] To provide interaction with a user, embodiments of the subject matter described in this specification may be implemented on a computer having a display device for displaying information to the user, such as an LCD (liquid crystal display), OLED (organic light emitting diode), or other monitor, and a keyboard and pointing device that the user can use to provide input to the computer, such as a mouse or trackball. Other kinds of devices may also be used to provide interaction with the user; for example, feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including acoustic, voice, or tactile input. In addition, a computer may interact with a user by sending documents to and receiving documents from a device used by the user; for example, by sending a web page to a web browser in response to a request received from the web browser on the user's device.
[0120] The embodiments of the subject matter described in this specification may be implemented in a computing system including a back-end component, such as a data server, or including a middleware component, such as an application server, or including a front-end component, such as a client computer with a graphical user interface or a web browser, through which a user can interact with a specific implementation of the subject matter described in this specification, or including any combination of one or more such back-end components, middleware components, or front-end components. The components of the system may be interconnected by digital data communication of any form or medium, such as a communication network. Examples of communication networks include local area networks (LANs) and wide area networks (WANs), such as the Internet.
[0121] The computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by means of a computer program that runs on a corresponding computer and has a client-server relationship with each other. In some embodiments, the server transmits data (e.g., a hypertext markup language (HTML) page) to a user device, for example, in order to display data to a user interacting with the user device acting as a client and to receive user input from a user interacting with the user device. Data generated at the user device can be received from the user device at the server, for example, the result of user interaction.
[0122] Figure 5 5 is a block diagram of computing devices 500, 550 that can be used to implement the systems and methods described in this specification as a client or as a server or multiple servers. Computing device 500 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Computing device 550 is intended to represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, smart watches, head-mounted devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions are meant to be exemplary only and are not meant to limit the specific implementations described and / or claimed in this specification.
[0123] The computing device 500 includes a processor 502, a memory 504, a storage device 506, a high-speed interface 508 connected to the memory 504 and a high-speed expansion port 510, and a low-speed interface 512 connected to a low-speed bus 514 and the storage device 506. Each of the components 502, 504, 506, 508, 510 and 512 is interconnected using various buses and can be mounted on a common motherboard or otherwise installed as appropriate. The processor 502 can process instructions for execution within the computing device 500, including instructions stored in the memory 504 or on the storage device 506 for displaying graphical information of a GUI on an external input / output device such as a display 516 coupled to the high-speed interface 508. In other specific implementations, multiple processors and / or multiple buses and multiple memories and memory types can be used as appropriate. Moreover, multiple computing devices 500 can be connected, each of which provides a portion of the necessary operations (for example, as a server bank, a group of blade servers, or a multi-processor system).
[0124] The memory 504 stores information within the computing device 500. In one implementation, the memory 504 is a computer-readable medium. In one implementation, the memory 504 is one or more volatile memory units. In another implementation, the memory 504 is one or more non-volatile memory units.
[0125] Storage device 506 can provide mass storage for computing device 500. In one specific implementation, storage device 506 is a computer readable medium. In various different specific implementations, storage device 506 can be a floppy disk device, a hard disk device, an optical disk device or a tape device, a flash memory or other similar solid-state memory device or device array, including devices in a storage area network or other configurations. In one specific implementation, a computer program product is tangibly embodied in an information carrier. The computer program product includes instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer readable medium or a machine readable medium, such as a memory 504, a storage device 506, or a memory on a processor 502.
[0126] The high-speed controller 508 manages bandwidth-intensive operations of the computing device 500, while the low-speed controller 512 manages less bandwidth-intensive operations. This allocation of responsibilities is exemplary only. In one specific implementation, the high-speed controller 508 is coupled to the memory 504, the display 516 (e.g., through a graphics processor or accelerator), and is coupled to a high-speed expansion port 510 that can accept various expansion cards (not shown). In a specific implementation, the low-speed controller 512 is coupled to the storage device 506 and the low-speed expansion port 514. The low-speed expansion port, which may include various communication ports (e.g., USB, Bluetooth, Ethernet, wireless Ethernet), can be coupled to one or more input / output devices, such as a keyboard, a pointing device, a scanner, or a networking device, such as a switch or a router, for example, through a network adapter.
[0127] Computing device 500 can be implemented in a variety of different forms, as shown. For example, it can be implemented as a standard server 520, or multiple times in a group of such servers. It can also be implemented as part of a rack server system 524. In addition, it can be implemented in a personal computer such as a laptop computer 522. Alternatively, components from computing device 500 can be combined with other components in a mobile device (not shown) such as device 550. Each of such devices can contain one or more of computing devices 500, 550, and the entire system can be composed of multiple computing devices 500, 550 that communicate with each other.
[0128] Computing device 550 includes processor 552, memory 564, input / output devices such as display 554, communication interface 566 and transceiver 568, among other components. Device 550 may also be provided with a storage device, such as a microdrive or other device, to provide additional storage. Each of components 550, 552, 564, 554, 566, and 568 are interconnected using various buses, and several of the components may be mounted on a common motherboard or otherwise as appropriate.
[0129] Processor 552 can process instructions for execution within computing device 550, including instructions stored in memory 564. Processors can also include separate analog and digital processors. The processor can, for example, provide coordination for other components of device 550, such as controlling a user interface, applications running by device 550, and wireless communications through device 550.
[0130] The processor 552 can communicate with the user through a control interface 558 and a display interface 556 coupled to the display 554. The display 554 can be, for example, a TFT LCD display or an OLED display, or other suitable display technology. The display interface 556 may include suitable circuits for driving the display 554 to present graphics and other information to the user. The control interface 558 can receive commands from the user and convert them for submission to the processor 552. In addition, an external interface 562 in communication with the processor 552 can be provided to enable nearby area communication of the device 550 with other devices. The external interface 562 can, for example, provide wired communication (e.g., through a docking program) or wireless communication (e.g., via Bluetooth or other such technologies).
[0131] The memory 564 stores information within the computing device 550. In one specific implementation, the memory 564 is a computer-readable medium. In one specific implementation, the memory 564 is one or more volatile memory units. In another specific implementation, the memory 564 is one or more non-volatile storage units. An expansion memory 574 may also be provided and connected to the device 550 via an expansion interface 572, which may include, for example, a SIMM card interface. Such an expansion memory 574 may provide additional storage space for the device 550, or may also store applications or other information for the device 550. Specifically, the expansion memory 574 may include instructions for executing or supplementing the above-mentioned processes, and may also include security information. Therefore, for example, the expansion memory 574 may be provided as a security module for the device 550, and may be programmed with instructions that allow the secure use of the device 550. In addition, security applications and additional information may be provided via a SIMM card, such as placing identification information on the SIMM card in an unbreakable manner.
[0132] The memory may include, for example, flash memory and / or MRAM memory, as discussed below. In one implementation, a computer program product is tangibly embodied in an information carrier. The computer program product includes instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer-readable medium or a machine-readable medium, such as the memory 564, the expansion memory 574, or a memory on the processor 552.
[0133] Device 550 can communicate wirelessly via communication interface 566, which may include digital signal processing circuitry where necessary. Communication interface 566 can provide communication in various modes or protocols, such as GSM voice calls, SMS, EMS or MMS messaging, CDMA, TDMA, PDC, WCDMA, CDMA2000, or GPRS, etc. Such communication can occur, for example, via radio frequency transceiver 568. In addition, short-range communication can occur, such as using Bluetooth, WiFi, or other such transceivers (not shown). In addition, GPS receiver module 570 can provide additional wireless data to device 550, which can be used as appropriate by applications running on device 550.
[0134] Device 550 may also communicate audibly using audio codec 560, which may receive verbal information from a user and convert the verbal information into usable digital information. Audio codec 560 may also generate audible sounds for the user, such as through a speaker, for example, in a telephone handset of device 550. Such sounds may include sounds from voice phone calls, may include recorded sounds (e.g., voice messages, music files, etc.), and may also include sounds generated by applications operating on device 550.
[0135] The computing device 550 can be implemented in many different forms, as shown in the figure. For example, it can be implemented as a cellular phone 580. It can also be implemented as a part of a smart phone 582, a personal digital assistant or other similar mobile device.
[0136] Various implementations of the systems and techniques described herein can be realized in digital electronic circuitry, integrated circuitry, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor that can be special or general purpose, at least one input device, and at least one output device, the programmable processor being coupled to receive data and instructions from a storage system and to transmit data and instructions to the storage system.
[0137] These computer programs (also referred to as programs, software, software applications or code) include machine instructions for a programmable processor and can be implemented in a high-level procedural language and / or an object-oriented programming language and / or in assembly language / machine language. As used herein, the terms "machine-readable medium", "computer-readable medium" refer to any computer program product, apparatus and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.
[0138] Although this specification includes many specific implementation details, these details should not be interpreted as limitations on the scope of the content claimed, but should be regarded as descriptions of features that may be peculiar to a particular embodiment. Certain features described in the context of different embodiments in this specification may also be implemented in combination in a single embodiment. On the contrary, the various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in the form of any suitable sub-combination. In addition, although certain features may be described above as acting in certain combinations and even initially claimed in this way, one or more features of the claimed combination may be removed from the combination in some cases, and the claimed combination may involve a sub-combination or a variation of the sub-combination.
[0139] Similarly, although the operations are shown in a particular order in the accompanying drawings, this should not be understood as requiring such operations to be performed in a sequential order or in the particular order shown, or requiring all the operations shown to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. In addition, the division of each system module and component in the above-mentioned embodiment should not be understood as requiring such division in all embodiments, and it should be understood that the program components and systems can be generally integrated together in a single software product or encapsulated in multiple software products.
[0140] In each case where an HTML file is mentioned, other file types or formats may be substituted. For example, an HTML file may be replaced by XML, JSON, plain text, or other types of files. Also, where a table or hash table is mentioned, other data structures (such as a spreadsheet, a relational database, or a structured file) may be used.
[0141] Specific embodiments of the present invention have been described. Other embodiments are within the scope of the following claims. For example, the steps recited in the claims, described in the specification, or depicted in the drawings can be performed in a different order and still achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. < / eop> < / sop> < / eop> < / sop>
Claims
1. A computer-implemented method comprising: Receiving, by the first device, a message including at least one element from the second device via a wireless network; determining whether the at least one element a) indicates that the message includes one or more phrases of an original message from the first device, and b) indicates that the message is not a reduced size message of the original message; determining whether to decompress the message using a first result of determining whether the at least one element a) indicates that the message includes the one or more phrases from the original message, and b) indicates that the message is not a reduced-size message of the original message; as well as One or more actions are performed based at least on a second result of determining whether to decompress the message.
2. The method of claim 1 , wherein performing the one or more actions comprises: generating a decompressed message including the one or more phrases based at least on the determination to decompress the message based at least on the at least one element from the message; as well as The one or more actions are performed based at least on the decompressed message including the one or more phrases.
3. The method of claim 2, wherein generating the decompressed message comprises: At least a portion of the original message is reconstructed based at least on the message and the decompression operation. The method of claim 3 , wherein the decompression operation uses a mapping of phrases to codes.
5. The method according to claim 1, wherein: Determining whether the at least one element indicates that the message includes the one or more phrases of the original message from the first device includes: determining whether the at least one element includes one or more key phrases and indicates that the message is not a reduced size message of the original message; and Performing the one or more actions is based at least on the one or more key phrases and in response to determining whether to decompress the message based at least on the one or more key phrases.
6. The method according to claim 1, comprising: After receiving the message, receiving the original message including the one or more phrases; as well as One or more updated actions are performed based at least on the original message including the one or more phrases.
7. The method according to claim 1, wherein: the at least one element indicating that the first device has a decompression engine for the message; and Determining whether to decompress the message includes: based on the at least one element indicating that the first device has a decompression engine for the message, and the at least one element indicating that the message does not include the one or more phrases from the original message, determining whether to use the first result of the determination to decompress the message using the decompression engine.
8. The method of claim 1, wherein: the at least one element indicating that the first device is part of an emergency services system; and Determining whether the at least one element represents the one or more phrases of the original message from the first device is based at least on the at least one element indicating that the first device is part of an emergency services system.
9. The method according to claim 1, wherein: The at least one element indicates that the first device has a predetermined address; and Determining whether the at least one element represents the one or more phrases of the original message from the first device is based at least on the at least one element indicating that the first device has the predetermined address.
10. The method of claim 1, wherein performing the one or more actions comprises presenting data for the one or more phrases and a location of the second device.
11. An apparatus comprising a processing circuit and a memory, the memory having instructions stored thereon, the instructions being operable, when executed by the processing circuit, to cause the processing circuit to perform an operation comprising: receiving a message including at least one element from a device via a wireless network; determining whether the at least one element a) indicates that the message includes one or more phrases of an original message from the device, and b) indicates that the message is not a reduced size message of the original message; determining whether to decompress the message using a first result of determining whether the at least one element a) indicates that the message includes the one or more phrases from the original message, and b) indicates that the message is not a reduced-size message of the original message; as well as One or more actions are performed based at least on a second result of determining whether to decompress the message.
12. The apparatus of claim 11, wherein performing the one or more actions comprises: generating a decompressed message including the one or more phrases based at least on the determination to decompress the message based at least on the at least one element from the message; as well as The one or more actions are performed based at least on the decompressed message including the one or more phrases.
13. The apparatus of claim 12, wherein generating the decompressed message comprises: At least a portion of the original message is reconstructed based at least on the message and the decompression operation.
14. The apparatus of claim 13, wherein the decompression operation uses a mapping of phrases to codes.
15. The device according to claim 11, wherein: Determining whether the at least one element indicates that the message includes the one or more phrases of the original message from the device includes: determining whether the at least one element includes one or more key phrases and indicates that the message is not a reduced size message of the original message; and Performing the one or more actions is based at least on the one or more key phrases and in response to determining whether to decompress the message based at least on the one or more key phrases.
16. The apparatus according to claim 11, comprising: After receiving the message, receiving the original message including the one or more phrases; as well as One or more updated actions are performed based at least on the original message including the one or more phrases.
17. The device according to claim 11, wherein: the at least one element indicating that the apparatus has a decompression engine for the message; and Determining whether to decompress the message includes: based on the at least one element indicating that the device has a decompression engine for the message, and the at least one element indicating that the message does not include the one or more phrases from the original message, determining whether to use the first result of the determination to decompress the message using the decompression engine.
18. The device of claim 11, wherein the at least one element indicates that the device is part of an emergency services system.
19. The device of claim 11, wherein the at least one element indicates that the device has a predetermined address.
20. The apparatus of claim 11, wherein performing the one or more actions comprises presenting data for the one or more phrases and a location of the device.
